Search

Objects we encounter often change appearance as we interact with them. Changes in illumination (shadows), object pose, or movement of nonrigid objects can drastically alter available image features. How do biological visual systems track objects as they change? It may involve specific attentional mechanisms for reasoning about the locations of objects independently of their appearances -- a capability that prominent neuroscientific theories have associated with computing through neural synchrony. We computationally test the hypothesis that the implementation of visual attention through neural synchrony underlies the ability of biological visual systems to track objects that change in appearance over time. We first introduce a novel deep learning circuit that can learn to precisely control attention to features separately from their location in the world through neural synchrony: the complex-valued recurrent neural network (CV-RNN). Next, we compare object tracking in humans, the CV-RNN, and other deep neural networks (DNNs), using FeatureTracker: a large-scale challenge that asks observers to track objects as their locations and appearances change in precisely controlled ways. While humans effortlessly solved FeatureTracker, state-of-the-art DNNs did not. In contrast, our CV-RNN behaved similarly to humans on the challenge, providing a computational proof-of-concept for the role of phase synchronization as a neural substrate for tracking appearance-morphing objects as they move about.

Humans can effortlessly draw new categories from a single exemplar, a feat that has long posed a challenge for generative models. However, this gap has started to close with recent advances in diffusion models. This one-shot drawing task requires powerful inductive biases that have not been systematically investigated. Here, we study how different inductive biases shape the latent space of Latent Diffusion Models (LDMs). Along with standard LDM regularizers (KL and vector quantization), we explore supervised regularizations (including classification and prototype-based representation) and contrastive inductive biases (using SimCLR and redundancy reduction objectives). We demonstrate that LDMs with redundancy reduction and prototype-based regularizations produce near-human-like drawings (regarding both samples' recognizability and originality) -- better mimicking human perception (as evaluated psychophysically). Overall, our results suggest that the gap between humans and machines in one-shot drawings is almost closed.

The convergence of artificial intelligence (AI) and Earth observation (EO) technologies has brought geoscience and remote sensing into an era of unparalleled capabilities. AI's transformative impact on data analysis, particularly derived from EO platforms, holds great promise in addressing global challenges such as environmental monitoring, disaster response and climate change analysis. However, the rapid integration of AI necessitates a careful examination of the responsible dimensions inherent in its application within these domains. In this paper, we represent a pioneering effort to systematically define the intersection of AI and EO, with a central focus on responsible AI practices. Specifically, we identify several critical components guiding this exploration from both academia and industry perspectives within the EO field: AI and EO for social good, mitigating unfair biases, AI security in EO, geo-privacy and privacy-preserving measures, as well as maintaining scientific excellence, open data, and guiding AI usage based on ethical principles. Furthermore, the paper explores potential opportunities and emerging trends, providing valuable insights for future research endeavors.

High-level visual brain regions contain subareas in which neurons appear to respond more strongly to examples of a particular semantic category, like faces or bodies, rather than objects. However, recent work has shown that while this finding holds on average, some out-of-category stimuli also activate neurons in these regions. This may be due to visual features common among the preferred class also being present in other images. Here, we propose a deep-learning-based approach for visualizing these features. For each neuron, we identify relevant visual features driving its selectivity by modelling responses to images based on latent activations of a deep neural network. Given an out-of-category image which strongly activates the neuron, our method first identifies a reference image from the preferred category yielding a similar feature activation pattern. We then backpropagate latent activations of both images to the pixel level, while enhancing the identified shared dimensions and attenuating non-shared features. The procedure highlights image regions containing shared features driving responses of the model neuron. We apply the algorithm to novel recordings from body-selective regions in macaque IT cortex in order to understand why some images of objects excite these neurons. Visualizations reveal object parts which resemble parts of a macaque body, shedding light on neural preference of these objects., Comment: Replaced by camera-ready version for NeurIPS 2024. Fixed some typos and a small inaccuracy in the method decription

Previous studies have shown that it is possible to map brain activation data of subjects viewing images onto the feature representation space of not only vision models (modality-specific decoding) but also language models (cross-modal decoding). In this work, we introduce and use a new large-scale fMRI dataset (~8,500 trials per subject) of people watching both images and text descriptions of such images. This novel dataset enables the development of modality-agnostic decoders: a single decoder that can predict which stimulus a subject is seeing, irrespective of the modality (image or text) in which the stimulus is presented. We train and evaluate such decoders to map brain signals onto stimulus representations from a large range of publicly available vision, language and multimodal (vision+language) models. Our findings reveal that (1) modality-agnostic decoders perform as well as (and sometimes even better than) modality-specific decoders (2) modality-agnostic decoders mapping brain data onto representations from unimodal models perform as well as decoders relying on multimodal representations (3) while language and low-level visual (occipital) brain regions are best at decoding text and image stimuli, respectively, high-level visual (temporal) regions perform well on both stimulus types., Comment: To appear at ICLR 2024 workshop on Representational Alignment (Re-Align)

Humans perceive the world through multiple senses, enabling them to create a comprehensive representation of their surroundings and to generalize information across domains. For instance, when a textual description of a scene is given, humans can mentally visualize it. In fields like robotics and Reinforcement Learning (RL), agents can also access information about the environment through multiple sensors; yet redundancy and complementarity between sensors is difficult to exploit as a source of robustness (e.g. against sensor failure) or generalization (e.g. transfer across domains). Prior research demonstrated that a robust and flexible multimodal representation can be efficiently constructed based on the cognitive science notion of a 'Global Workspace': a unique representation trained to combine information across modalities, and to broadcast its signal back to each modality. Here, we explore whether such a brain-inspired multimodal representation could be advantageous for RL agents. First, we train a 'Global Workspace' to exploit information collected about the environment via two input modalities (a visual input, or an attribute vector representing the state of the agent and/or its environment). Then, we train a RL agent policy using this frozen Global Workspace. In two distinct environments and tasks, our results reveal the model's ability to perform zero-shot cross-modal transfer between input modalities, i.e. to apply to image inputs a policy previously trained on attribute vectors (and vice-versa), without additional training or fine-tuning. Variants and ablations of the full Global Workspace (including a CLIP-like multimodal representation trained via contrastive learning) did not display the same generalization abilities., Comment: Under review in a conference

Land use expansion is linked to major sustainability concerns including climate change, food security and biodiversity loss. This expansion is largely concentrated in so-called frontiers, defined here as places experiencing marked transformations due to rapid resource exploitation. Understanding the mechanisms shaping these frontiers is crucial for sustainability. Previous work focused mainly on explaining how active frontiers advance, in particular into tropical forests. Comparatively, our understanding of how frontiers emerge in territories considered marginal in terms of agricultural productivity and global market integration remains weak. We synthesize conceptual tools explaining resource and land-use frontiers, including theories of land rent and agglomeration economies, of frontiers as successive waves, spaces of territorialization, friction, and opportunities, anticipation and expectation. We then propose a new theory of frontier emergence, which identifies exogenous pushes, legacies of past waves, and actors anticipations as key mechanisms by which frontiers emerge. Processes of abnormal rent creation and capture and the built-up of agglomeration economies then constitute key mechanisms sustaining active frontiers. Finally, we discuss five implications for the governance of frontiers for sustainability. Our theory focuses on agriculture and deforestation frontiers in the tropics, but can be inspirational for other frontier processes including for extractive resources, such as minerals.

In recent years, driven by the need for safer and more autonomous transport systems, the automotive industry has shifted toward integrating a growing number of Advanced Driver Assistance Systems (ADAS). Among the array of sensors employed for object recognition tasks, radar sensors have emerged as a formidable contender due to their abilities in adverse weather conditions or low-light scenarios and their robustness in maintaining consistent performance across diverse environments. However, the small size of radar datasets and the complexity of the labelling of those data limit the performance of radar object detectors. Driven by the promising results of self-supervised learning in computer vision, this paper presents RiCL, an instance contrastive learning framework to pre-train radar object detectors. We propose to exploit the detection from the radar and the temporal information to pre-train the radar object detection model in a self-supervised way using contrastive learning. We aim to pre-train an object detector's backbone, head and neck to learn with fewer data. Experiments on the CARRADA and the RADDet datasets show the effectiveness of our approach in learning generic representations of objects in range-Doppler maps. Notably, our pre-training strategy allows us to use only 20% of the labelled data to reach a similar mAP@0.5 than a supervised approach using the whole training set., Comment: 8 pages, 3 figures, 1 table

Transfer learning allows for resource-efficient geographic transfer of pre-trained field delineation models. However, the scarcity of labeled data for complex and dynamic smallholder landscapes, particularly in Sub-Saharan Africa, remains a major bottleneck for large-area field delineation. This study explores opportunities of using sparse field delineation pseudo labels for fine-tuning models across geographies and sensor characteristics. We build on a FracTAL ResUNet trained for crop field delineation in India (median field size of 0.24 ha) and use this pre-trained model to generate pseudo labels in Mozambique (median field size of 0.06 ha). We designed multiple pseudo label selection strategies and compared the quantities, area properties, seasonal distribution, and spatial agreement of the pseudo labels against human-annotated training labels (n = 1,512). We then used the human-annotated labels and the pseudo labels for model fine-tuning and compared predictions against human field annotations (n = 2,199). Our results indicate i) a good baseline performance of the pre-trained model in both field delineation and field size estimation, and ii) the added value of regional fine-tuning with performance improvements in nearly all experiments. Moreover, we found iii) substantial performance increases when using only pseudo labels (up to 77% of the IoU increases and 68% of the RMSE decreases obtained by human labels), and iv) additional performance increases when complementing human annotations with pseudo labels. Pseudo labels can be efficiently generated at scale and thus facilitate domain adaptation in label-scarce settings. The workflow presented here is a stepping stone for overcoming the persisting data gaps in heterogeneous smallholder agriculture of Sub-Saharan Africa, where labels are commonly scarce.

Whether current or near-term AI systems could be conscious is a topic of scientific interest and increasing public concern. This report argues for, and exemplifies, a rigorous and empirically grounded approach to AI consciousness: assessing existing AI systems in detail, in light of our best-supported neuroscientific theories of consciousness. We survey several prominent scientific theories of consciousness, including recurrent processing theory, global workspace theory, higher-order theories, predictive processing, and attention schema theory. From these theories we derive "indicator properties" of consciousness, elucidated in computational terms that allow us to assess AI systems for these properties. We use these indicator properties to assess several recent AI systems, and we discuss how future systems might implement them. Our analysis suggests that no current AI systems are conscious, but also suggests that there are no obvious technical barriers to building AI systems which satisfy these indicators.

Attribution methods correspond to a class of explainability methods (XAI) that aim to assess how individual inputs contribute to a model's decision-making process. We have identified a significant limitation in one type of attribution methods, known as ``white-box" methods. Although highly efficient, as we will show, these methods rely on a gradient signal that is often contaminated by high-frequency artifacts. To overcome this limitation, we introduce a new approach called "FORGrad". This simple method effectively filters out these high-frequency artifacts using optimal cut-off frequencies tailored to the unique characteristics of each model architecture. Our findings show that FORGrad consistently enhances the performance of already existing white-box methods, enabling them to compete effectively with more accurate yet computationally demanding "black-box" methods. We anticipate that our research will foster broader adoption of simpler and more efficient white-box methods for explainability, offering a better balance between faithfulness and computational efficiency.

Recent deep learning models can efficiently combine inputs from different modalities (e.g., images and text) and learn to align their latent representations, or to translate signals from one domain to another (as in image captioning, or text-to-image generation). However, current approaches mainly rely on brute-force supervised training over large multimodal datasets. In contrast, humans (and other animals) can learn useful multimodal representations from only sparse experience with matched cross-modal data. Here we evaluate the capabilities of a neural network architecture inspired by the cognitive notion of a "Global Workspace": a shared representation for two (or more) input modalities. Each modality is processed by a specialized system (pretrained on unimodal data, and subsequently frozen). The corresponding latent representations are then encoded to and decoded from a single shared workspace. Importantly, this architecture is amenable to self-supervised training via cycle-consistency: encoding-decoding sequences should approximate the identity function. For various pairings of vision-language modalities and across two datasets of varying complexity, we show that such an architecture can be trained to align and translate between two modalities with very little need for matched data (from 4 to 7 times less than a fully supervised approach). The global workspace representation can be used advantageously for downstream classification tasks and for robust transfer learning. Ablation studies reveal that both the shared workspace and the self-supervised cycle-consistency training are critical to the system's performance., Comment: Under review

Every day, the human brain processes an immense volume of visual information, relying on intricate neural mechanisms to perceive and interpret these stimuli. Recent breakthroughs in functional magnetic resonance imaging (fMRI) have enabled scientists to extract visual information from human brain activity patterns. In this study, we present an innovative method for decoding brain activity into meaningful images and captions, with a specific focus on brain captioning due to its enhanced flexibility as compared to brain decoding into images. Our approach takes advantage of cutting-edge image captioning models and incorporates a unique image reconstruction pipeline that utilizes latent diffusion models and depth estimation. We utilized the Natural Scenes Dataset, a comprehensive fMRI dataset from eight subjects who viewed images from the COCO dataset. We employed the Generative Image-to-text Transformer (GIT) as our backbone for captioning and propose a new image reconstruction pipeline based on latent diffusion models. The method involves training regularized linear regression models between brain activity and extracted features. Additionally, we incorporated depth maps from the ControlNet model to further guide the reconstruction process. We evaluate our methods using quantitative metrics for both generated captions and images. Our brain captioning approach outperforms existing methods, while our image reconstruction pipeline generates plausible images with improved spatial relationships. In conclusion, we demonstrate significant progress in brain decoding, showcasing the enormous potential of integrating vision and language to better understand human cognition. Our approach provides a flexible platform for future research, with potential applications in various fields, including neural art, style transfer, and portable devices.

Sensory perception (e.g. vision) relies on a hierarchy of cortical areas, in which neural activity propagates in both directions, to convey information not only about sensory inputs but also about cognitive states, expectations and predictions. At the macroscopic scale, neurophysiological experiments have described the corresponding neural signals as both forward and backward-travelling waves, sometimes with characteristic oscillatory signatures. It remains unclear, however, how such activity patterns relate to specific functional properties of the perceptual apparatus. Here, we present a mathematical framework, inspired by neural network models of predictive coding, to systematically investigate neural dynamics in a hierarchical perceptual system. We show that stability of the system can be systematically derived from the values of hyper-parameters controlling the different signals (related to bottom-up inputs, top-down prediction and error correction). Similarly, it is possible to determine in which direction, and at what speed neural activity propagates in the system. Different neural assemblies (reflecting distinct eigenvectors of the connectivity matrices) can simultaneously and independently display different properties in terms of stability, propagation speed or direction. We also derive continuous-limit versions of the system, both in time and in neural space. Finally, we analyze the possible influence of transmission delays between layers, and reveal the emergence of oscillations at biologically plausible frequencies.

In neural decoding research, one of the most intriguing topics is the reconstruction of perceived natural images based on fMRI signals. Previous studies have succeeded in re-creating different aspects of the visuals, such as low-level properties (shape, texture, layout) or high-level features (category of objects, descriptive semantics of scenes) but have typically failed to reconstruct these properties together for complex scene images. Generative AI has recently made a leap forward with latent diffusion models capable of generating high-complexity images. Here, we investigate how to take advantage of this innovative technology for brain decoding. We present a two-stage scene reconstruction framework called ``Brain-Diffuser''. In the first stage, starting from fMRI signals, we reconstruct images that capture low-level properties and overall layout using a VDVAE (Very Deep Variational Autoencoder) model. In the second stage, we use the image-to-image framework of a latent diffusion model (Versatile Diffusion) conditioned on predicted multimodal (text and visual) features, to generate final reconstructed images. On the publicly available Natural Scenes Dataset benchmark, our method outperforms previous models both qualitatively and quantitatively. When applied to synthetic fMRI patterns generated from individual ROI (region-of-interest) masks, our trained model creates compelling ``ROI-optimal'' scenes consistent with neuroscientific knowledge. Thus, the proposed methodology can have an impact on both applied (e.g. brain-computer interface) and fundamental neuroscience.

Research in machine learning has polarized into two general approaches for regression tasks: Transductive methods construct estimates directly from available data but are usually problem unspecific. Inductive methods can be much more specific but generally require compute-intensive solution searches. In this work, we propose a hybrid approach and show that transductive regression principles can be meta-learned through gradient descent to form efficient in-context neural approximators by leveraging the theory of vector-valued Reproducing Kernel Banach Spaces (RKBS). We apply this approach to function spaces defined over finite and infinite-dimensional spaces (function-valued operators) and show that once trained, the Transducer can almost instantaneously capture an infinity of functional relationships given a few pairs of input and output examples and return new image estimates. We demonstrate the benefit of our meta-learned transductive approach to model complex physical systems influenced by varying external factors with little data at a fraction of the usual deep learning training computational cost for partial differential equations and climate modeling applications.

Automotive radar sensors provide valuable information for advanced driving assistance systems (ADAS). Radars can reliably estimate the distance to an object and the relative velocity, regardless of weather and light conditions. However, radar sensors suffer from low resolution and huge intra-class variations in the shape of objects. Exploiting the time information (e.g., multiple frames) has been shown to help to capture better the dynamics of objects and, therefore, the variation in the shape of objects. Most temporal radar object detectors use 3D convolutions to learn spatial and temporal information. However, these methods are often non-causal and unsuitable for real-time applications. This work presents RECORD, a new recurrent CNN architecture for online radar object detection. We propose an end-to-end trainable architecture mixing convolutions and ConvLSTMs to learn spatio-temporal dependencies between successive frames. Our model is causal and requires only the past information encoded in the memory of the ConvLSTMs to detect objects. Our experiments show such a method's relevance for detecting objects in different radar representations (range-Doppler, range-angle) and outperform state-of-the-art models on the ROD2021 and CARRADA datasets while being less computationally expensive., Comment: 11 pages, 4 figures, 5 tables

Reconstructing perceived natural images from fMRI signals is one of the most engaging topics of neural decoding research. Prior studies had success in reconstructing either the low-level image features or the semantic/high-level aspects, but rarely both. In this study, we utilized an Instance-Conditioned GAN (IC-GAN) model to reconstruct images from fMRI patterns with both accurate semantic attributes and preserved low-level details. The IC-GAN model takes as input a 119-dim noise vector and a 2048-dim instance feature vector extracted from a target image via a self-supervised learning model (SwAV ResNet-50); these instance features act as a conditioning for IC-GAN image generation, while the noise vector introduces variability between samples. We trained ridge regression models to predict instance features, noise vectors, and dense vectors (the output of the first dense layer of the IC-GAN generator) of stimuli from corresponding fMRI patterns. Then, we used the IC-GAN generator to reconstruct novel test images based on these fMRI-predicted variables. The generated images presented state-of-the-art results in terms of capturing the semantic attributes of the original test images while remaining relatively faithful to low-level image details. Finally, we use the learned regression model and the IC-GAN generator to systematically explore and visualize the semantic features that maximally drive each of several regions-of-interest in the human brain.

Deep Reinforcement Learning has demonstrated the potential of neural networks tuned with gradient descent for solving complex tasks in well-delimited environments. However, these neural systems are slow learners producing specialized agents with no mechanism to continue learning beyond their training curriculum. On the contrary, biological synaptic plasticity is persistent and manifold, and has been hypothesized to play a key role in executive functions such as working memory and cognitive flexibility, potentially supporting more efficient and generic learning abilities. Inspired by this, we propose to build networks with dynamic weights, able to continually perform self-reflexive modification as a function of their current synaptic state and action-reward feedback, rather than a fixed network configuration. The resulting model, MetODS (for Meta-Optimized Dynamical Synapses) is a broadly applicable meta-reinforcement learning system able to learn efficient and powerful control rules in the agent policy space. A single layer with dynamic synapses can perform one-shot learning, generalizes navigation principles to unseen environments and manifests a strong ability to learn adaptive motor policies., Comment: Published at Neurips 2022

The human hippocampus possesses "concept cells", neurons that fire when presented with stimuli belonging to a specific concept, regardless of the modality. Recently, similar concept cells were discovered in a multimodal network called CLIP (Radford et at., 2021). Here, we ask whether CLIP can explain the fMRI activity of the human hippocampus better than a purely visual (or linguistic) model. We extend our analysis to a range of publicly available uni- and multi-modal models. We demonstrate that "multimodality" stands out as a key component when assessing the ability of a network to explain the multivoxel activity in the hippocampus., Comment: Oral at SVRHM Workshop (NeurIPS 2021)

Visual understanding requires comprehending complex visual relations between objects within a scene. Here, we seek to characterize the computational demands for abstract visual reasoning. We do this by systematically assessing the ability of modern deep convolutional neural networks (CNNs) to learn to solve the "Synthetic Visual Reasoning Test" (SVRT) challenge, a collection of twenty-three visual reasoning problems. Our analysis reveals a novel taxonomy of visual reasoning tasks, which can be primarily explained by both the type of relations (same-different vs. spatial-relation judgments) and the number of relations used to compose the underlying rules. Prior cognitive neuroscience work suggests that attention plays a key role in humans' visual reasoning ability. To test this hypothesis, we extended the CNNs with spatial and feature-based attention mechanisms. In a second series of experiments, we evaluated the ability of these attention networks to learn to solve the SVRT challenge and found the resulting architectures to be much more efficient at solving the hardest of these visual reasoning tasks. Most importantly, the corresponding improvements on individual tasks partially explained our novel taxonomy. Overall, this work provides an granular computational account of visual reasoning and yields testable neuroscience predictions regarding the differential need for feature-based vs. spatial attention depending on the type of visual reasoning problem., Comment: 26 pages, 16 figures

Brain-inspired machine learning is gaining increasing consideration, particularly in computer vision. Several studies investigated the inclusion of top-down feedback connections in convolutional networks; however, it remains unclear how and when these connections are functionally helpful. Here we address this question in the context of object recognition under noisy conditions. We consider deep convolutional networks (CNNs) as models of feed-forward visual processing and implement Predictive Coding (PC) dynamics through feedback connections (predictive feedback) trained for reconstruction or classification of clean images. To directly assess the computational role of predictive feedback in various experimental situations, we optimize and interpret the hyper-parameters controlling the network's recurrent dynamics. That is, we let the optimization process determine whether top-down connections and predictive coding dynamics are functionally beneficial. Across different model depths and architectures (3-layer CNN, ResNet18, and EfficientNetB0) and against various types of noise (CIFAR100-C), we find that the network increasingly relies on top-down predictions as the noise level increases; in deeper networks, this effect is most prominent at lower layers. In addition, the accuracy of the network implementing PC dynamics significantly increases over time-steps, compared to its equivalent forward network. All in all, our results provide novel insights relevant to Neuroscience by confirming the computational role of feedback connections in sensory systems, and to Machine Learning by revealing how these can improve the robustness of current vision models., Comment: 'Andrea Alamia' and 'Milad Mozafari' contributed equally to this work

Deep neural networks excel at image classification, but their performance is far less robust to input perturbations than human perception. In this work we explore whether this shortcoming may be partly addressed by incorporating brain-inspired recurrent dynamics in deep convolutional networks. We take inspiration from a popular framework in neuroscience: 'predictive coding'. At each layer of the hierarchical model, generative feedback 'predicts' (i.e., reconstructs) the pattern of activity in the previous layer. The reconstruction errors are used to iteratively update the network's representations across timesteps, and to optimize the network's feedback weights over the natural image dataset-a form of unsupervised training. We show that implementing this strategy into two popular networks, VGG16 and EfficientNetB0, improves their robustness against various corruptions and adversarial attacks. We hypothesize that other feedforward networks could similarly benefit from the proposed framework. To promote research in this direction, we provide an open-sourced PyTorch-based package called Predify, which can be used to implement and investigate the impacts of the predictive coding dynamics in any convolutional neural network., Comment: Paper presented at NeurIPS 2021

Vision models trained on multimodal datasets can benefit from the wide availability of large image-caption datasets. A recent model (CLIP) was found to generalize well in zero-shot and transfer learning settings. This could imply that linguistic or "semantic grounding" confers additional generalization abilities to the visual feature space. Here, we systematically evaluate various multimodal architectures and vision-only models in terms of unsupervised clustering, few-shot learning, transfer learning and adversarial robustness. In each setting, multimodal training produced no additional generalization capability compared to standard supervised visual training. We conclude that work is still required for semantic grounding to help improve vision models., Comment: Paper accepted at the CoNLL 2021 conference. This version: section added on the performance of the visual and visio-linguistic models on linquistic tasks

Transformer attention architectures, similar to those developed for natural language processing, have recently proved efficient also in vision, either in conjunction with or as a replacement for convolutional layers. Typically, visual attention is inserted in the network architecture as a (series of) feedforward self-attention module(s), with mutual key-query agreement as the main selection and routing operation. However efficient, this strategy is only vaguely compatible with the way that attention is implemented in biological brains: as a separate and unified network of attentional selection regions, receiving inputs from and exerting modulatory influence on the entire hierarchy of visual regions. Here, we report experiments with a simple such attention system that can improve the performance of standard convolutional networks, with relatively few additional parameters. Each spatial position in each layer of the network produces a key-query vector pair; all queries are then pooled into a global attention query. On the next iteration, the match between each key and the global attention query modulates the network's activations -- emphasizing or silencing the locations that agree or disagree (respectively) with the global attention system. We demonstrate the usefulness of this brain-inspired Global Attention Agreement network (GAttANet) for various convolutional backbones (from a simple 5-layer toy model to a standard ResNet50 architecture) and datasets (CIFAR10, CIFAR100, Imagenet-1k). Each time, our global attention system improves accuracy over the corresponding baseline., Comment: Paper accepted to ICANN 2021 - The 30th International Conference on Artificial Neural Networks

Modern feedforward convolutional neural networks (CNNs) can now solve some computer vision tasks at super-human levels. However, these networks only roughly mimic human visual perception. One difference from human vision is that they do not appear to perceive illusory contours (e.g. Kanizsa squares) in the same way humans do. Physiological evidence from visual cortex suggests that the perception of illusory contours could involve feedback connections. Would recurrent feedback neural networks perceive illusory contours like humans? In this work we equip a deep feedforward convolutional network with brain-inspired recurrent dynamics. The network was first pretrained with an unsupervised reconstruction objective on a natural image dataset, to expose it to natural object contour statistics. Then, a classification decision layer was added and the model was finetuned on a form discrimination task: squares vs. randomly oriented inducer shapes (no illusory contour). Finally, the model was tested with the unfamiliar ''illusory contour'' configuration: inducer shapes oriented to form an illusory square. Compared with feedforward baselines, the iterative ''predictive coding'' feedback resulted in more illusory contours being classified as physical squares. The perception of the illusory contour was measurable in the luminance profile of the image reconstructions produced by the model, demonstrating that the model really ''sees'' the illusion. Ablation studies revealed that natural image pretraining and feedback error correction are both critical to the perception of the illusion. Finally we validated our conclusions in a deeper network (VGG): adding the same predictive coding feedback dynamics again leads to the perception of illusory contours., Comment: Manuscript under review

Recent advances in deep learning have allowed Artificial Intelligence (AI) to reach near human-level performance in many sensory, perceptual, linguistic or cognitive tasks. There is a growing need, however, for novel, brain-inspired cognitive architectures. The Global Workspace theory refers to a large-scale system integrating and distributing information among networks of specialized modules to create higher-level forms of cognition and awareness. We argue that the time is ripe to consider explicit implementations of this theory using deep learning techniques. We propose a roadmap based on unsupervised neural translation between multiple latent spaces (neural networks trained for distinct tasks, on distinct sensory inputs and/or modalities) to create a unique, amodal global latent workspace (GLW). Potential functional advantages of GLW are reviewed, along with neuroscientific implications., Comment: This version with improved text and figures

Despite their elegant formulation and lightweight memory cost, neural ordinary differential equations (NODEs) suffer from known representational limitations. In particular, the single flow learned by NODEs cannot express all homeomorphisms from a given data space to itself, and their static weight parameterization restricts the type of functions they can learn compared to discrete architectures with layer-dependent weights. Here, we describe a new module called neurally controlled ODE (N-CODE) designed to improve the expressivity of NODEs. The parameters of N-CODE modules are dynamic variables governed by a trainable map from initial or current activation state, resulting in forms of open-loop and closed-loop control, respectively. A single module is sufficient for learning a distribution on non-autonomous flows that adaptively drive neural representations. We provide theoretical and empirical evidence that N-CODE circumvents limitations of previous NODEs models and show how increased model expressivity manifests in several supervised and unsupervised learning problems. These favorable empirical results indicate the potential of using data- and activity-dependent plasticity in neural networks across numerous domains.

Decoding and reconstructing images from brain imaging data is a research area of high interest. Recent progress in deep generative neural networks has introduced new opportunities to tackle this problem. Here, we employ a recently proposed large-scale bi-directional generative adversarial network, called BigBiGAN, to decode and reconstruct natural scenes from fMRI patterns. BigBiGAN converts images into a 120-dimensional latent space which encodes class and attribute information together, and can also reconstruct images based on their latent vectors. We computed a linear mapping between fMRI data, acquired over images from 150 different categories of ImageNet, and their corresponding BigBiGAN latent vectors. Then, we applied this mapping to the fMRI activity patterns obtained from 50 new test images from 50 unseen categories in order to retrieve their latent vectors, and reconstruct the corresponding images. Pairwise image decoding from the predicted latent vectors was highly accurate (84%). Moreover, qualitative and quantitative assessments revealed that the resulting image reconstructions were visually plausible, successfully captured many attributes of the original images, and had high perceptual similarity with the original content. This method establishes a new state-of-the-art for fMRI-based natural image reconstruction, and can be flexibly updated to take into account any future improvements in generative models of natural scene images., Comment: Accepted to IEEE IJCNN2020

In recent years artificial neural networks achieved performance close to or better than humans in several domains: tasks that were previously human prerogatives, such as language processing, have witnessed remarkable improvements in state of the art models. One advantage of this technological boost is to facilitate comparison between different neural networks and human performance, in order to deepen our understanding of human cognition. Here, we investigate which neural network architecture (feed-forward vs. recurrent) matches human behavior in artificial grammar learning, a crucial aspect of language acquisition. Prior experimental studies proved that artificial grammars can be learnt by human subjects after little exposure and often without explicit knowledge of the underlying rules. We tested four grammars with different complexity levels both in humans and in feedforward and recurrent networks. Our results show that both architectures can 'learn' (via error back-propagation) the grammars after the same number of training sequences as humans do, but recurrent networks perform closer to humans than feedforward ones, irrespective of the grammar complexity level. Moreover, similar to visual processing, in which feedforward and recurrent architectures have been related to unconscious and conscious processes, our results suggest that explicit learning is best modeled by recurrent architectures, whereas feedforward networks better capture the dynamics involved in implicit learning.

While objects from different categories can be reliably decoded from fMRI brain response patterns, it has proved more difficult to distinguish visually similar inputs, such as different instances of the same category. Here, we apply a recently developed deep learning system to the reconstruction of face images from human fMRI patterns. We trained a variational auto-encoder (VAE) neural network using a GAN (Generative Adversarial Network) unsupervised training procedure over a large dataset of celebrity faces. The auto-encoder latent space provides a meaningful, topologically organized 1024-dimensional description of each image. We then presented several thousand face images to human subjects, and learned a simple linear mapping between the multi-voxel fMRI activation patterns and the 1024 latent dimensions. Finally, we applied this mapping to novel test images, turning the obtained fMRI patterns into VAE latent codes, and ultimately the codes into face reconstructions. Qualitative and quantitative evaluation of the reconstructions revealed robust pairwise decoding (>95% correct), and a strong improvement relative to a baseline model (PCA decomposition). Furthermore, this brain decoding model can readily be recycled to probe human face perception along many dimensions of interest; for example, the technique allowed for accurate gender classification, and even to decode which face was imagined, rather than seen by the subject. We hypothesize that the latent space of modern deep learning generative models could serve as a valid approximation for human brain representations.

A semi-empirical method is applied to calculate the time-average sound level of wind turbine noise generation and propagation. Both are affected by wind shear refraction. Under upwind conditions the partially ensonified zone separates the fully ensonified zone (close to the turbine) and the shadow zone (far away from the turbine). Refraction is described in terms of the wind speed linear profile fitted to the power law profile. The rotating blades are treated as a two-dimensional circular source in the vertical plane. Inside the partially ensonified zone the effective A-weighted sound power decreases to zero when the receiver moves from the turbine toward the shadow zone. The presented results would be useful in practical applications to give a quick estimate of the effect of refraction on wind turbine noise., Comment: 17 pages, 8 figures, submitted to International Journal of Aeroacoustics

Due to swish and thump amplitude modulation, the noise of wind turbines cause more annoyance than other environmental noise of the same average level. The wind shear accounts for the thump modulation (van den Berg effect). Making use of the wind speed measurements at the hub height, as well as at the top and the bottom of the rotor disc (Fig.1), the non-standard wind profile is applied. It causes variations in the A-weighted sound pressure level, LpA. The difference between the maximum and minimum of LpA characterizes thump modulation (Fig.2)., Comment: 13 pages, 8 figures, submitted to Acta Acustica united with Acustica