Search Results for author:
Found 43 papers, 6 papers with code
Jointly learning visual motion and confidence from local patches in event cameras
In the task of recovering pan-tilt ego velocities from events, we show that each individual confident local prediction of our network can be expected to be as accurate as state of the art optimization approaches which utilize the full image.
Parametric Matrix Models
We present a general class of machine learning algorithms called parametric matrix models.
TimewarpVAE: Simultaneous Time-Warping and Representation Learning of Trajectories
Human demonstrations of trajectories are an important source of training data for many machine learning problems.
Sparsity-depth Tradeoff in Infinitely Wide Deep Neural Networks
We investigate how sparse neural activity affects the generalization performance of a deep Bayesian neural network at the large width limit.
EV-Catcher: High-Speed Object Catching Using Low-latency Event-based Neural Networks
Event-based sensors have recently drawn increasing interest in robotic perception due to their lower latency, higher dynamic range, and lower bandwidth requirements compared to standard CMOS-based imagers.
Policy-Value Alignment and Robustness in Search-based Multi-Agent Learning
Large-scale AI systems that combine search and learning have reached super-human levels of performance in game-playing, but have also been shown to fail in surprising ways.
Multi-Agent Curricula and Emergent Implicit Signaling
We show that pursuers trained with our strategy exchange more than twice as much information (in bits) than baseline methods, indicating that our method has learned, and relies heavily on, the exchange of implicit signals.
Cooperative Multi-Agent Fairness and Equivariant Policies
We study fairness through the lens of cooperative multi-agent learning.
Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization
There have been many recent advances in representation learning; however, unsupervised representation learning can still struggle with model identification issues related to rotations of the latent space.
Learning Continuous Cost-to-Go Functions for Non-holonomic Systems
In this work, we show that uniform sampling fails for non-holonomic systems.
Cost-to-Go Function Generating Networks for High Dimensional Motion Planning
The c2g-HOF architecture consists of a cost-to-go function over the configuration space represented as a neural network (c2g-network) as well as a Higher Order Function (HOF) network which outputs the weights of the c2g-network for a given input workspace.
Low-Bandwidth Communication Emerges Naturally in Multi-Agent Learning Systems
In this work, we study emergent communication through the lens of cooperative multi-agent behavior in nature.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Fast Motion Understanding with Spatiotemporal Neural Networks and Dynamic Vision Sensors
This paper presents a Dynamic Vision Sensor (DVS) based system for reasoning about high speed motion.
Learning to Track Dynamic Targets in Partially Known Environments
In particular, we introduce Active Tracking Target Network (ATTN), a unified RL policy that is capable of solving major sub-tasks of active target tracking -- in-sight tracking, navigation, and exploration.
Geodesic-HOF: 3D Reconstruction Without Cutting Corners
To address this issue, we propose learning an image-conditioned mapping function from a canonical sampling domain to a high dimensional space where the Euclidean distance is equal to the geodesic distance on the object.
Near-chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection
This paper presents a novel end-to-end system for pedestrian detection using Dynamic Vision Sensors (DVSs).
Surface HOF: Surface Reconstruction from a Single Image Using Higher Order Function Networks
Our approach is to learn a Higher Order Function (HOF) which takes an image of an object as input and generates a mapping function.
Learning Q-network for Active Information Acquisition
In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest using on-board sensors.
Higher Order Function Networks for View Planning and Multi-View Reconstruction
In contrast to offline methods which require a 3D model of the object as input or online methods which rely on only local measurements, our method uses a neural network which encodes shape information for a large number of objects.
Higher-Order Function Networks for Learning Composable 3D Object Representations
We present a new approach to 3D object representation where a neural network encodes the geometry of an object directly into the weights and biases of a second 'mapping' network.
Probabilistically Safe Corridors to Guide Sampling-Based Motion Planning
In this paper, we introduce a new probabilistically safe local steering primitive for sampling-based motion planning in complex high-dimensional configuration spaces.
Robotics
U-Net for MAV-based Penstock Inspection: an Investigation of Focal Loss in Multi-class Segmentation for Corrosion Identification
Periodical inspection and maintenance of critical infrastructure such as dams, penstocks, and locks are of significant importance to prevent catastrophic failures.
Learning Optimal Resource Allocations in Wireless Systems
This paper considers the design of optimal resource allocation policies in wireless communication systems which are generically modeled as a functional optimization problem with stochastic constraints.
Scalable Centralized Deep Multi-Agent Reinforcement Learning via Policy Gradients
When the number of agents increases, the dimensionality of the input and control spaces increase as well, and these methods do not scale well.
Distributed Optimization
Multi-agent Reinforcement Learning
+2
Nearest neighbor density functional estimation from inverse Laplace transform
A new approach to $L_2$-consistent estimation of a general density functional using $k$-nearest neighbor distances is proposed, where the functional under consideration is in the form of the expectation of some function $f$ of the densities at each point.
Assumed Density Filtering Q-learning
We formulate an efficient closed-form solution for the value update by approximately estimating analytic parameters of the posterior of the Q-beliefs.
Generative Local Metric Learning for Kernel Regression
This paper shows how metric learning can be used with Nadaraya-Watson (NW) kernel regression.
Classification and Geometry of General Perceptual Manifolds
The effects of label sparsity on the classification capacity of manifolds are elucidated, revealing a scaling relation between label sparsity and manifold radius.
Memory Augmented Control Networks
The third part uses a network controller that learns to store those specific instances of past information that are necessary for planning.
Learning Data Manifolds with a Cutting Plane Method
We consider the problem of classifying data manifolds where each manifold represents invariances that are parameterized by continuous degrees of freedom.
Neural Network Memory Architectures for Autonomous Robot Navigation
This work is a first thorough study of memory structures for deep-neural-network-based robot navigation, and offers novel tools to train such networks from supervision and quantify their ability to generalize to unseen scenarios.
Efficient Neural Codes under Metabolic Constraints
The advantage could be as large as one-fold, substantially larger than the previous estimation.
Linear Readout of Object Manifolds
Objects are represented in sensory systems by continuous manifolds due to sensitivity of neuronal responses to changes in physical features such as location, orientation, and intensity.
Belief Flows of Robust Online Learning
This paper introduces a new probabilistic model for online learning which dynamically incorporates information from stochastic gradients of an arbitrary loss function.
An Adversarial Interpretation of Information-Theoretic Bounded Rationality
Here, we show that a single-agent free energy optimization is equivalent to a game between the agent and an imaginary adversary.
Optimal Neural Population Codes for High-dimensional Stimulus Variables
We consider solutions for a minimal case where the number of neurons in the population is equal to the number of stimulus dimensions (diffeomorphic).
Diffusion Decision Making for Adaptive k-Nearest Neighbor Classification
This paper sheds light on some fundamental connections of the diffusion decision making model of neuroscience and cognitive psychology with k-nearest neighbor classification.
Optimal Neural Tuning Curves for Arbitrary Stimulus Distributions: Discrimax, Infomax and Minimum L_p Loss
In this manner, we show how the optimal tuning curve depends upon the loss function, and the equivalence of maximizing mutual information with minimizing $L_p$ loss in the limit as $p$ goes to zero.
Generative Local Metric Learning for Nearest Neighbor Classification
We consider the problem of learning a local metric to enhance the performance of nearest neighbor classification.
Learning via Gaussian Herding
We introduce a new family of online learning algorithms based upon constraining the velocity flow over a distribution of weight vectors.
Extended Grassmann Kernels for Subspace-Based Learning
Subspace-based learning problems involve data whose elements are linear subspaces of a vector space.
Algorithms for Non-negative Matrix Factorization
Non-negative matrix factorization (NMF) has previously been shown to be a useful decomposition for multivariate data.
A Neural Network Based Head Tracking System
We have constructed an inexpensive video based motorized tracking system that learns to track a head.
