Completed

Efficient Object Detection with Super High-Resolution Image

Object detection in Ultra High-Resolution (UHR) images has long been a challenging problem in computer vision due to the varying scales of the targeted objects. When it comes to barcode detection, resizing UHR input images to smaller sizes often leads to the loss of pertinent information, while processing them directly is highly in-...

Multi-task Learning with Safe and Differentiable Policies

Generalization capability to new tasks or environments is crucial to deploy autonomous agents like robots and self-driving vehicles at scale in the real-world. This is extremely challenging and often requires the agent to perform state-specific reasoning such as in model-based planning and control. Optimization-based meta-learning methods like MAML [1] have been shown to tackle multi-task adaptation problems, but the inner-loop optimization contained in those methods makes them hard to train in an end-to-end fashion. Differentiable and end-to-end learning for planning [2] and...

Differentiable Optimization for Game Theoretic Formulations

Game theory is an effective tool in formulating interactions among agents and finds its use in many real world challenges including human-robot interaction scenarios, like self-driving. Recently, such tools have also found applications in machine learning [1,2] and reinforcement learning [3] domains. For example, virtual agents in the form of optimizer and uncertainties in robust optimization, the E-step and M-step in EM algorithm [4,5], and the model adaptation and policy update in model-based RL [6]. Typically real world problems like self-driving are represented as general-...

Learning Non-Intuitive Physics in Children and Adults

In this project, we will explore whether children and adults can learn non-intuitive physicalforces, particularly those that violate our core knowledge about the physical world, and whether thislearning varies as a function of age. For example, can children and adults who are exploring andinteracting with VR worlds learn that...

Mitigating Emergent Biases in Online Learning

The field of online learning and bandits deals with sequential decision-making problems, where a learner performs a series of decisions aimed at minimizing (or maximizing) a loss (or reward) signal. Online learning algorithms are the basis of many data driven systems used to drive consequential decisions in internet commerce, finance and even policing. There has...

LP-based Algorithms for Reinforcement Learning

Since its introduction a decade ago, relative entropy policy search (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains, not to mention providing algorithmic components used by many recently proposed reinforcement learning (RL) algorithms....

Semantic Depth Extraction for Indoor Scenes

We investigated methods for combining the strengths of semantic (instance) segmentation and monocular depth estimation to predict sharp, high-quality relative depth maps for Augmented Reality applications.

Researchers Utkarsh Singhal, UC Berkeley, s.utkarsh@berkey.edu Stella Yu, UC Berkeley, stellayu@berkeley.edu Chun Kai Wang, Amazon,...

Generalization Bounds for Interpolating Deep Neural Networks

We study the training of finite-width two-layer smoothed ReLU networks for binary classification using the logistic loss. We show that gradient descent drives the training loss to zero if the initial loss is small enough. When the data satisfies certain cluster and separation conditions and the network is wide enough, we show that one step of gradient descent reduces the loss sufficiently that the first result applies. In contrast, all past analyses of fixed-width networks that we know do not guarantee that the training loss goes to zero.

Update...

Agnostic Reinforcement Learning

Our goal is to understand the possibility of performing online control of an unknown dynamical system while making minimal assumptions regarding the underlying dynamics. In particular, we consider the problem of adaptively controlling the linear quadratic regulator whose states transitions lie inside a rich, nonlinear function space, such as an infinite dimensional RKHS.

Update

Completion Report...

Generalizing Neural Radiance Fields

Coordinate-based neural representations for low dimensional signals are becoming increasingly popular in computer vision and graphics. In particular, these fully-...