Search

The identification of molecular structure is essential for understanding chemical diversity and for developing drug leads from small molecules. Nevertheless, the structure elucidation of small molecules by Nuclear Magnetic Resonance (NMR) experiments is often a long and non-trivial process that relies on years of training. To achieve this process efficiently, several spectral databases have been established to retrieve reference NMR spectra. However, the number of reference NMR spectra available is limited and has mostly facilitated annotation of commercially available derivatives. Here, we introduce DeepSAT, a neural network-based structure annotation and scaffold prediction system that directly extracts the chemical features associated with molecular structures from their NMR spectra. Using only the 1H-13C HSQC spectrum, DeepSAT identifies related known compounds and thus efficiently assists in the identification of molecular structures. DeepSAT is expected to accelerate chemical and biomedical research by accelerating the identification of molecular structures. [ABSTRACT FROM AUTHOR]

The identification of molecular structure is essential for understanding chemical diversity and for developing drug leads from small molecules. Nevertheless, the structure elucidation of small molecules by Nuclear Magnetic Resonance (NMR) experiments is often a long and non-trivial process that relies on years of training. To achieve this process efficiently, several spectral databases have been established to retrieve reference NMR spectra. However, the number of reference NMR spectra available is limited and has mostly facilitated annotation of commercially available derivatives. Here, we introduce DeepSAT, a neural network-based structure annotation and scaffold prediction system that directly extracts the chemical features associated with molecular structures from their NMR spectra. Using only the 1H-13C HSQC spectrum, DeepSAT identifies related known compounds and thus efficiently assists in the identification of molecular structures. DeepSAT is expected to accelerate chemical and biomedical research by accelerating the identification of molecular structures. [ABSTRACT FROM AUTHOR]

Research has shown that climate change creates warmer temperatures and drier conditions, leading to longer wildfire seasons and increased wildfire risks in the United States. These factors have, in turn, led to increases in the frequency, extent, and severity of wildfires in recent years. Given the danger posed by wildland fires to people, property, wildlife, and the environment, there is an urgent need to provide tools for effective wildfire management. Early detection of wildfires is essential to minimizing potentially catastrophic destruction. To that end, in this paper, we present our work on integrating multiple data sources into SmokeyNet, a deep learning model using spatiotemporal information to detect smoke from wildland fires. We present Multimodal SmokeyNet and SmokeyNet Ensemble for multimodal wildland fire smoke detection using satellite-based fire detections, weather sensor measurements, and optical camera images. An analysis is provided to compare these multimodal approaches to the baseline SmokeyNet in terms of accuracy metrics, as well as time-to-detect, which is important for the early detection of wildfires. Our results show that incorporating weather data in SmokeyNet improves performance numerically in terms of both F1 and time-to-detect over the baseline with a single data source. With a time-to-detect of only a few minutes, SmokeyNet can be used for automated early notification of wildfires, providing a useful tool in the fight against destructive wildfires. [ABSTRACT FROM AUTHOR]

The identification of metabolites from complex biofluids and extracts of tissues is an essential process for understanding metabolic profiles. Nuclear magnetic resonance (NMR) spectroscopy is widely used in metabolomics studies for identification and quantification of metabolites. However, the accurate identification of individual metabolites is still a challenging process with higher peak intensity or similar chemical shifts from different metabolites. In this study, we applied a convolutional neural network (CNN) to 1H‐13C HSQC NMR spectra to achieve accurate peak identification in complex mixtures. The results reveal that the neural network was successfully trained on metabolite identification from these 2D NMR spectra and achieved very good performance compared with other NMR‐based metabolomic tools. [ABSTRACT FROM AUTHOR]

Incomplete time series classification (ITSC) is an important issue in time series analysis since temporal data often has missing values in practical applications. However, integrating imputation (replacing missing data) and classification within a model often rapidly amplifies the error from imputed values. Reducing this error propagation from imputation to classification remains a challenge. To this end, we propose an adversarial joint-learning recurrent neural network (AJ-RNN) for ITSC, an end-to-end model trained in an adversarial and joint learning manner. We train the system to categorize the time series as well as impute missing values. To alleviate the error introduced by each imputation value, we use an adversarial network to encourage the network to impute realistic missing values by distinguishing real and imputed values. Hence, AJ-RNN can directly perform classification with missing values and greatly reduce the error propagation from imputation to classification, boosting the accuracy. Extensive experiments on 68 synthetic datasets and 4 real-world datasets from the expanded UCR time series archive demonstrate that AJ-RNN achieves state-of-the-art performance. Furthermore, we show that our model can effectively alleviate the accumulating error problem through qualitative and quantitative analysis based on the trajectory of the dynamical system learned by the RNN. We also provide an analysis of the model behavior to verify the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Time series with missing values (incomplete time series) are ubiquitous in real life on account of noise or malfunctioning sensors. Time-series imputation (replacing missing data) remains a challenge due to the potential for nonlinear dependence on concurrent and previous values of the time series. In this paper, we propose a novel framework for modeling incomplete time series, called a linear memory vector recurrent neural network (LIME-RNN), a recurrent neural network (RNN) with a learned linear combination of previous history states. The technique bears some similarity to residual networks and graph-based temporal dependency imputation. In particular, we introduce a linear memory vector [called the residual sum vector (RSV)] that integrates over previous hidden states of the RNN, and is used to fill in missing values. A new loss function is developed to train our model with time series in the presence of missing values in an end-to-end way. Our framework can handle imputation of both missing-at-random and consecutive missing inputs. Moreover, when conducting time-series prediction with missing values, LIME-RNN allows imputation and prediction simultaneously. We demonstrate the efficacy of the model via extensive experimental evaluation on univariate and multivariate time series, achieving state-of-the-art performance on synthetic and real-world data. The statistical results show that our model is significantly better than most existing time-series univariate or multivariate imputation methods. [ABSTRACT FROM AUTHOR]

Do dopaminergic reward structures represent the expected utility of information similarly to a reward? Optimal experimental design models from Bayesian decision theory and statistics have proposed a theoretical framework for quantifying the expected value of information that might result from a query. In particular, this formulation quantifies the value of information before the answer to that query is known, in situations where payoffs are unknown and the goal is purely epistemic: That is, to increase knowledge about the state of the world. Whether and how such a theoretical quantity is represented in the brain is unknown. Here we use an event-related functional MRI (fMRI) task design to disentangle information expectation, information revelation and categorization outcome anticipation, and response-contingent reward processing in a visual probabilistic categorization task. We identify a neural signature corresponding to the expectation of information, involving the left lateral ventral striatum. Moreover, we show a temporal dissociation in the activation of different reward-related regions, including the nucleus accumbens, medial prefrontal cortex, and orbitofrontal cortex, during information expectation versus reward-related processing. [ABSTRACT FROM AUTHOR]

An amendment to this paper has been published and can be accessed via a link at the top of the paper. [ABSTRACT FROM AUTHOR]

Saliency detection, finding the most important parts of an image, has become increasingly popular in computer vision. In this paper, we introduce Hierarchical Cellular Automata (HCA)—a temporally evolving model to intelligently detect salient objects. HCA consists of two main components: Single-layer Cellular Automata (SCA) and Cuboid Cellular Automata (CCA). As an unsupervised propagation mechanism, Single-layer Cellular Automata can exploit the intrinsic relevance of similar regions through interactions with neighbors. Low-level image features as well as high-level semantic information extracted from deep neural networks are incorporated into the SCA to measure the correlation between different image patches. With these hierarchical deep features, an impact factor matrix and a coherence matrix are constructed to balance the influences on each cell’s next state. The saliency values of all cells are iteratively updated according to a well-defined update rule. Furthermore, we propose CCA to integrate multiple saliency maps generated by SCA at different scales in a Bayesian framework. Therefore, single-layer propagation and multi-scale integration are jointly modeled in our unified HCA. Surprisingly, we find that the SCA can improve all existing methods that we applied it to, resulting in a similar precision level regardless of the original results. The CCA can act as an efficient pixel-wise aggregation algorithm that can integrate state-of-the-art methods, resulting in even better results. Extensive experiments on four challenging datasets demonstrate that the proposed algorithm outperforms state-of-the-art conventional methods and is competitive with deep learning based approaches. [ABSTRACT FROM AUTHOR]

Various algorithms comparing 2D NMR spectra have been explored for their ability to dereplicate natural products as well as determine molecular structures. However, spectroscopic artefacts, solvent effects, and the interactive effect of functional group(s) on chemical shifts combine to hinder their effectiveness. Here, we leveraged Non-Uniform Sampling (NUS) 2D NMR techniques and deep Convolutional Neural Networks (CNNs) to create a tool, SMART, that can assist in natural products discovery efforts. First, an NUS heteronuclear single quantum coherence (HSQC) NMR pulse sequence was adapted to a state-of-the-art nuclear magnetic resonance (NMR) instrument, and data reconstruction methods were optimized, and second, a deep CNN with contrastive loss was trained on a database containing over 2,054 HSQC spectra as the training set. To demonstrate the utility of SMART, several newly isolated compounds were automatically located with their known analogues in the embedded clustering space, thereby streamlining the discovery pipeline for new natural products. [ABSTRACT FROM AUTHOR]

We trained a neurocomputational model on six categories of photographic images that were used in a previous fMRI study of object and face processing. Multivariate pattern analyses of the activations elicited in the object-encoding layer of the model yielded results consistent with two previous, contradictory fMRI studies. Findings from one of the studies [Haxby, J. V., Gobbini, M. I., Furey, M. L., Ishai, A., Schouten, J. L., & Pietrini, P. Distributed and overlapping representations of faces and objects in ventral temporal cortex. Science, 293, 2425-2430, 2001] were interpreted as evidence for the object-form topography model. Findings from the other study [Spiridon, M., & Kanwisher, N. How distributed is visual category information in human occipitotemporal cortex? An fMRI study. Neuron, 35, 1157-1165, 2002] were interpreted as evidence for neural processing mechanisms in the fusiform face area that are specialized for faces. Because the model contains no special processing mechanism or specialized architecture for faces and yet it can reproduce the fMRI findings used to support the claim that there are specialized face-processing neurons, we argue that these fMRI results do not actually support that claim. Results from our neurocomputational model therefore constitute a cautionary tale for the interpretation of fMRI data. [ABSTRACT FROM AUTHOR]

The size and frequency of wildland fires in the western United States have dramatically increased in recent years. On high-fire-risk days, a small fire ignition can rapidly grow and become out of control. Early detection of fire ignitions from initial smoke can assist the response to such fires before they become difficult to manage. Past deep learning approaches for wildfire smoke detection have suffered from small or unreliable datasets that make it difficult to extrapolate performance to real-world scenarios. In this work, we present the Fire Ignition Library (FIgLib), a publicly available dataset of nearly 25,000 labeled wildfire smoke images as seen from fixed-view cameras deployed in Southern California. We also introduce SmokeyNet, a novel deep learning architecture using spatiotemporal information from camera imagery for real-time wildfire smoke detection. When trained on the FIgLib dataset, SmokeyNet outperforms comparable baselines and rivals human performance. We hope that the availability of the FIgLib dataset and the SmokeyNet architecture will inspire further research into deep learning methods for wildfire smoke detection, leading to automated notification systems that reduce the time to wildfire response. [ABSTRACT FROM AUTHOR]

Hemispheric asymmetry in the processing of local and global features has been argued to originate from differences in frequency filtering in the two hemispheres, with little neuro-physiological support. Here we test the hypothesis that this asymmetry takes place at an encoding stage beyond the sensory level, due to asymmetries in anatomical connections within each hemisphere. We use two simple encoding networks with differential connection structures as models of differential encoding in the two hemispheres based on a hypothesized generalization of neuroanatomical evidence from the auditory modality to the visual modality: The connection structure between columns is more distal in the language areas of the left hemisphere and more local in the homotopic regions in the right hemisphere. We show that both processing differences and differential frequency filtering can arise naturally in this neurocomputational model with neuroanatomically inspired differences in connection structures within the two model hemispheres, suggesting that hemispheric asymmetry in the processing of local and global features may be due to hemispheric asymmetry in connection structure rather than in frequency tuning. [ABSTRACT FROM AUTHOR]

A damage detection approach is developed using nonlinear autoregressive with exogenous inputs (NARX) neural networks and a statistical inference technique. Within a large spatially extended dynamic system, an instrumented local substructure may be represented by a neural network, to predict the dynamic response of a given sensor from that of its neighbors. Without change in the system properties, the network prediction error will follow a stable statistical distribution. To infer damage, change in the prediction error variance as evaluated by the statistical inference standard test is utilized as a sensitive indicator. Validation of the described procedure is undertaken using two experimental data sets (from the Los Alamos National Laboratory in Los Alamos, NM). Reduced stiffness and nonlinear response of a mass-spring system is documented in the first set, while joint damage in a frame structure is explored in the second. Favorable results are obtained in both cases with linear/nonlinear and single/multidamage patterns. Overall, the proposed framework may be particularly efficient for large spatially extended sensor network situations, where local condition assessment may be conducted based on the response of a few neighboring sensors. [ABSTRACT FROM AUTHOR]

In image recognition it is often assumed the method used to convert color images to grayscale has little impact on recognition performance. We compare thirteen different grayscale algorithms with four types of image descriptors and demonstrate that this assumption is wrong: not all color-to-grayscale algorithms work equally well, even when using descriptors that are robust to changes in illumination. These methods are tested using a modern descriptor-based image recognition framework, on face, object, and texture datasets, with relatively few training instances. We identify a simple method that generally works best for face and object recognition, and two that work well for recognizing textures. [ABSTRACT FROM AUTHOR]

Decision processes in simultaneous lineups (an array of faces in which a 'suspect' face is displayed along with foil faces) were examined using eye tracking to capture the length and number of times that individual faces were visually analysed. The similarity of the lineup target face relative to the study face was manipulated, and face dwell times on the first visit and on return visits to the individual lineup faces were measured. On first visits, positively identified faces were examined for a longer duration compared to faces that were not identified. When no face was identified from the lineup, the suspect was visited for a longer duration compared to a foil face. On return visits, incorrectly identified faces were examined for a longer duration and visited more often compared to correctly identified faces. The results indicate that lineup decisions can be predicted by face dwell time and the number of visits made to faces. Copyright © 2010 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

This paper describes an online stereo visual simultaneous localization and mapping (SLAM) algorithm developed for the Learning Applied to Ground Robotics (LAGR) program. The Gamma-SLAM algorithm uses a Rao–Blackwellized particle filter to obtain a joint posterior over poses and maps: the pose distribution is estimated using a particle filter, and each particle has its own map that is obtained through exact filtering conditioned on the particle's pose. Visual odometry is used to provide good proposal distributions for the particle filter, and maps are represented using a Cartesian grid. Unlike previous grid-based SLAM algorithms, however, the Gamma-SLAM map maintains a posterior distribution over the elevation variance in each cell. This variance grid map can capture rocks, vegetation, and other objects that are typically found in unstructured environments but are not well modeled by traditional occupancy or elevation grid maps. The algorithm runs in real time on conventional processors and has been evaluated for both qualitative and quantitative accuracy in three outdoor environments over trajectories totaling 1,600 m in length. © 2008 Wiley Periodicals, Inc. [ABSTRACT FROM AUTHOR]

Anatomical evidence shows that our visual field is initially split along the vertical midline and contralaterally projected to different hemispheres. It remains unclear at which processing stage the split information converges. In the current study, we applied the Double Filtering by Frequency (DFF) theory (Ivry & Robertson, 1998) to modeling the visual field split; the theory assumes a right-hemisphere/low-frequency bias. We compared three cognitive architectures with different timings of convergence and examined their cognitive plausibility to account for the left-side bias effect in face perception observed in human data. We show that the early convergence model failed to show the left-side bias effect. The modeling, hence, suggests that the convergence may take place at an intermediate or late stage, at least after information has been extracted/encoded separately in the two hemispheres, a fact that is often overlooked in computational modeling of cognitive processes. Comparative anatomical data suggest that this separate encoding process that results in differential frequency biases in the two hemispheres may be engaged from V1 up to the level of area V3a and V4v, and converge at least after the lateral occipital region. The left-side bias effect in our model was also observed in Greeble recognition; the modeling, hence, also provides testable predictions about whether the left-side bias effect may also be observed in (expertise-level) object recognition. [ABSTRACT FROM AUTHOR]

In the leech, the command-like neuron called cell Tr2 is known to stop swimming, but the connections from cell Tr2 to the swim central pattern generator have not been identified. We used fluorescence resonance energy transfer voltage-sensitive dyes to identify three neurons that are synaptic targets of cell Tr2. We then used electrophysiological techniques to show that these connections are monosyn- aptic, chemical, and excitatory. Two of the novel targets, cell 256 and cell 54, terminate swimming when stimulated. These neurons are likely to mediate swim cessation caused by cell Tr2 activity, and thus play the role of intermediate control cells in the leech CNS. [ABSTRACT FROM AUTHOR]

There are two competing theories of facial expression recognition. Some researchers have suggested that it is an example of "categorical perception." In this view, expression categories are considered to be discrete entities with sharp boundaries, and discrimination of nearby pairs of expressive faces is enhanced near those boundaries. Other researchers, however, suggest that facial expression perception is more graded and that facial expressions are best thought of as points in a continuous, low-dimensional space, where, for instance, "surprise" expressions lie between "happiness" and "fear" expressions due to their perceptual similarity. In this article, we show that a simple yet biologically plausible neural network model, trained to classify facial expressions into six basic emotions, predicts data used to support both of these theories. Without any parameter tuning, the model matches a variety of psychological data on categorization, similarity, reaction times, discrimination, and recognition difficulty, both qualitatively and quantitatively. We thus explain many of the seemingly complex psychological phenomena related to facial expression perception as natural consequences of the tasks' implementations in the brain. [ABSTRACT FROM AUTHOR]

We present and analyze a model of a two-cell reciprocally inhibitory network that oscillates. The principal mechanism of oscillation is short-term synaptic depression. Using a simple model of depression and analyzing the system in certain limits, we can derive analytical expressions for various features of the oscillation, including the parameter regime in which stable oscillations occur, as well as the period and amplitude of these oscillations. These expressions are functions of three parameters: the time constant of depression, the synaptic strengths, and the amount of tonic excitation the cells receive. We compare our analytical results with the output of numerical simulations and obtain good agreement between the two. Based on our analysis, we conclude that the oscillations in our network are qualitatively different from those in networks that oscillate due to postinhibitory rebound, spike-frequency adaptation, or other intrinsic (rather than synaptic) adaptational mechanisms. In particular, our network can oscillate only via the synaptic escape mode of Skinner, Kopell, and Marder (1994). [ABSTRACT FROM AUTHOR]

Presents a study which examined a method used for the automatic adjusting of parameters in ranked-output text retrieval systems to improve retrieval performance. Information on a ranked-output text retrieval system; Demonstration of the utility of the approach by using it to estimate a similarity measure; What experimental results using several collections indicated.

Proposes an indexing algorithm, called Metric Similarity Modeling (MSM), for representing documents based explicitly on semantic relationships between documents in addition to the individual term usage in documents. MSM application on standard text databases; Retrieval of semantically related documents; Improvement of document retrieval performance.

Explores a model of the process of generation of phonological forms. Connectionist network that generates one phoneme at a time from a fixed representation of the meaning of the word; Semantics' influence on the acquisition of adult forms; Source of children's production errors; Role of phonological form in molding children's vocabularies.

Presents a simple model of symbolic manipulation in artificial intelligence using a connectionist network called parallel distributed processing (PDP) that learned a procedure to add two multi-digit numbers. Demonstration that networks of such type can learn simple programming constructs that are not tested; Ability to process long problems; Power difference between simple recurrent networks and Fordan networks.

Presents a humorous commentary of the use of neural networks in the field of dognitive science. Utilization by dogmatists to determine to effect of neural networks on the concepts of dognitive science; Humorous types of models suggested to cognitions of dogs.

Proposes degenerative grammar (DG) as an alternative approach to generative grammar, whose approaches to the study of dog language have failed in their accounts of polysemy and the development of language comprehension. Meaning is deceptualization as the basic assumption of DG; Hypothesis that the central mold is built out of the young dog's initial experiences.

Presents a tongue-and-cheek discussion of efforts on the construction of user-friendly interfaces to computer systems. Approaches to interface design; Problems with outmoded command languages.

Presents a computer model of a competency theory on the sequential behavior of a dog. Use of randomly wired recurrent network with habituation in the weights; Boredom as the emergent property of the proposed model.

Presents a humorous suggestion of recreating the cultural atmosphere of the sixties through backpropagation in time. Allusion to the term back propagation to time travel; Artificial recreation and combination models of Jimi Hendrix and prohibited drugs in recurrent parallel distributed processing (PDP) networks.

Presents a humorous article about dog signal processing (DSP). Need for a good bark recognition; Advantage of working on bark recognition; Basis of the bark recognition system.

Investigates connectionist formalism or connectionism for modeling the dog. Extension of the model to investigate sub-primate language use; Simplification of the task of language study; Independence of the comprehension system from the generation system; Main result of the investigation.

Presents a humorous article on the fundamental problems in the philosophy of Dognitive Science. How to achieve dog breath; Computer simulation; Comparison with Sirloin's Chinese restaurant.

Focuses on the humour about human-dog relationship, as been evidenced by the attempts to make dogs more user-friendly. Why the attempts at dog-human interfaces have floundered on a basic misunderstanding of the dog; How dogs should be programmed; Dog's brain structure; Intentional behavior design of dogs.