Search

Three-dimensional (3D) ultrasound (US) imaging addresses the limitation in field-of-view (FOV) in conventional two-dimensional (2D) US imaging by providing 3D viewing of the anatomy. 3D US imaging has been extensively adapted for diagnosis and image-guided surgical intervention. However, conventional approaches to implement 3D US imaging require either expensive and sophisticated 2D array transducers, or external actuation mechanisms to move a one-dimensional array mechanically. Here, we propose a 3D US imaging mechanism using actuated acoustic reflector instead of the sensor elements for volume acquisition with significantly extended 3D FOV, which can be implemented with simple hardware and compact size. To improve image quality on the elevation plane, we introduce an adaptive-delay synthetic aperture focusing (AD-SAF) method for elevation beamforming. We first evaluated the proposed imaging mechanism and AD-SAF with simulated point targets and cysts targets. Results of point targets suggested improved image quality on the elevation plane, and results of cysts targets demonstrated a potential to improve 3D visualization of human anatomy. We built a prototype imaging system that has a 3D FOV of 38 mm (lateral) by 38 mm (elevation) by 50 mm (axial) and collected data in imaging experiments with phantoms. Experimental data showed consistency with simulation results. The AD-SAF method enhanced quantifying the cyst volume size in the breast mimicking phantom compared to without elevation beamforming. These results suggested that the proposed 3D US imaging mechanism could potentially be applied in clinical scenarios., Comment: 9 pages, 13 figures, in submission process to a journal

Making sophisticated, robust, and safe sequential decisions is at the heart of intelligent systems. This is especially critical for planning in complex multi-agent environments, where agents need to anticipate other agents' intentions and possible future actions. Traditional methods formulate the problem as a Markov Decision Process, but the solutions often rely on various assumptions and become brittle when presented with corner cases. In contrast, deep reinforcement learning (Deep RL) has been very effective at finding policies by simultaneously exploring, interacting, and learning from environments. Leveraging the powerful Deep RL paradigm, we demonstrate that an iterative procedure of self-play can create progressively more diverse environments, leading to the learning of sophisticated and robust multi-agent policies. We demonstrate this in a challenging multi-agent simulation of merging traffic, where agents must interact and negotiate with others in order to successfully merge on or off the road. While the environment starts off simple, we increase its complexity by iteratively adding an increasingly diverse set of agents to the agent "zoo" as training progresses. Qualitatively, we find that through self-play, our policies automatically learn interesting behaviors such as defensive driving, overtaking, yielding, and the use of signal lights to communicate intentions to other agents. In addition, quantitatively, we show a dramatic improvement of the success rate of merging maneuvers from 63% to over 98%., Comment: Autonomous Driving Workshop, IEEE International Conference on Computer Vision (ICCV 2019)

In this work, we introduce a new method for imitation learning from video demonstrations. Our method, Relational Mimic (RM), improves on previous visual imitation learning methods by combining generative adversarial networks and relational learning. RM is flexible and can be used in conjunction with other recent advances in generative adversarial imitation learning to better address the need for more robust and sample-efficient approaches. In addition, we introduce a new neural network architecture that improves upon the previous state-of-the-art in reinforcement learning and illustrate how increasing the relational reasoning capabilities of the agent enables the latter to achieve increasingly higher performance in a challenging locomotion task with pixel inputs. Finally, we study the effects and contributions of relational learning in policy evaluation, policy improvement and reward learning through ablation studies.

Recent advances in deep reinforcement learning have demonstrated the capability of learning complex control policies from many types of environments. When learning policies for safety-critical applications, it is essential to be sensitive to risks and avoid catastrophic events. Towards this goal, we propose an actor-critic framework that models the uncertainty of the future and simultaneously learns a policy based on that uncertainty model. Specifically, given a distribution of the future return for any state and action, we optimize policies for varying levels of conditional Value-at-Risk. The learned policy can map the same state to different actions depending on the propensity for risk. We demonstrate the effectiveness of our approach in the domain of driving simulations, where we learn maneuvers in two scenarios. Our learned controller can dynamically select actions along a continuous axis, where safe and conservative behaviors are found at one end while riskier behaviors are found at the other. Finally, when testing with very different simulation parameters, our risk-averse policies generalize significantly better compared to other reinforcement learning approaches., Comment: Conference on Robot Learning 2019 (CoRL 2019)

Temporal prediction is critical for making intelligent and robust decisions in complex dynamic environments. Motion prediction needs to model the inherently uncertain future which often contains multiple potential outcomes, due to multi-agent interactions and the latent goals of others. Towards these goals, we introduce a probabilistic framework that efficiently learns latent variables to jointly model the multi-step future motions of agents in a scene. Our framework is data-driven and learns semantically meaningful latent variables to represent the multimodal future, without requiring explicit labels. Using a dynamic attention-based state encoder, we learn to encode the past as well as the future interactions among agents, efficiently scaling to any number of agents. Finally, our model can be used for planning via computing a conditional probability density over the trajectories of other agents given a hypothetical rollout of the 'self' agent. We demonstrate our algorithms by predicting vehicle trajectories of both simulated and real data, demonstrating the state-of-the-art results on several vehicle trajectory datasets., Comment: In proceedings of NeurIPS 2019, Vancouver, British Columbia, Canada

Attention has long been proposed by psychologists as important for effectively dealing with the enormous sensory stimulus available in the neocortex. Inspired by the visual attention models in computational neuroscience and the need of object-centric data for generative models, we describe for generative learning framework using attentional mechanisms. Attentional mechanisms can propagate signals from region of interest in a scene to an aligned canonical representation, where generative modeling takes place. By ignoring background clutter, generative models can concentrate their resources on the object of interest. Our model is a proper graphical model where the 2D Similarity transformation is a part of the top-down process. A ConvNet is employed to provide good initializations during posterior inference which is based on Hamiltonian Monte Carlo. Upon learning images of faces, our model can robustly attend to face regions of novel test subjects. More importantly, our model can learn generative models of new faces from a novel dataset of large images where the face locations are not known., Comment: In the proceedings of Neural Information Processing Systems, 2014

The ICML 2013 Workshop on Challenges in Representation Learning focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge. We describe the datasets created for these challenges and summarize the results of the competitions. We provide suggestions for organizers of future challenges and some comments on what kind of knowledge can be gained from machine learning competitions., Comment: 8 pages, 2 figures

Recently, fully-connected and convolutional neural networks have been trained to achieve state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification, natural language processing, and bioinformatics. For classification tasks, most of these "deep learning" models employ the softmax activation function for prediction and minimize cross-entropy loss. In this paper, we demonstrate a small but consistent advantage of replacing the softmax layer with a linear support vector machine. Learning minimizes a margin-based loss instead of the cross-entropy loss. While there have been various combinations of neural nets and SVMs in prior art, our results using L2-SVMs show that by simply replacing softmax with linear SVMs gives significant gains on popular deep learning datasets MNIST, CIFAR-10, and the ICML 2013 Representation Learning Workshop's face expression recognition challenge., Comment: Contribution to the ICML 2013 Challenges in Representation Learning Workshop

Visual perception is a challenging problem in part due to illumination variations. A possible solution is to first estimate an illumination invariant representation before using it for recognition. The object albedo and surface normals are examples of such representations. In this paper, we introduce a multilayer generative model where the latent variables include the albedo, surface normals, and the light source. Combining Deep Belief Nets with the Lambertian reflectance assumption, our model can learn good priors over the albedo from 2D images. Illumination variations can be explained by changing only the lighting latent variable in our model. By transferring learned knowledge from similar objects, albedo and surface normals estimation from a single image is possible in our model. Experiments demonstrate that our model is able to generalize as well as improve over standard baselines in one-shot face recognition., Comment: Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)

An efficient way to learn deep density models that have many layers of latent variables is to learn one layer at a time using a model that has only one layer of latent variables. After learning each layer, samples from the posterior distributions for that layer are used as training data for learning the next layer. This approach is commonly used with Restricted Boltzmann Machines, which are undirected graphical models with a single hidden layer, but it can also be used with Mixtures of Factor Analysers (MFAs) which are directed graphical models. In this paper, we present a greedy layer-wise learning algorithm for Deep Mixtures of Factor Analysers (DMFAs). Even though a DMFA can be converted to an equivalent shallow MFA by multiplying together the factor loading matrices at different levels, learning and inference are much more efficient in a DMFA and the sharing of each lower-level factor loading matrix by many different higher level MFAs prevents overfitting. We demonstrate empirically that DMFAs learn better density models than both MFAs and two types of Restricted Boltzmann Machine on a wide variety of datasets., Comment: ICML2012