Search Results for author:
Found 11 papers, 7 papers with code
Resampling-free Particle Filters in High-dimensions
State estimation is crucial for the performance and safety of numerous robotic applications.
Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity
Deep reinforcement learning methods exhibit impressive performance on a range of tasks but still struggle on hard exploration tasks in large environments with sparse rewards.
Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building
Agents build and use a local map to predict their observations; high surprisal leads to a "fragmentation event" that truncates the local map.
Model-agnostic Measure of Generalization Difficulty
The measure of a machine learning algorithm is the difficulty of the tasks it can perform, and sufficiently difficult tasks are critical drivers of strong machine learning models.
Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
Double descent is a surprising phenomenon in machine learning, in which as the number of model parameters grows relative to the number of data, test error drops as models grow ever larger into the highly overparameterized (data undersampled) regime.
How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective
Recent works have examined theoretical and empirical properties of wide neural networks trained in the Neural Tangent Kernel (NTK) regime.
Fast Training of Provably Robust Neural Networks by SingleProp
Recent works have developed several methods of defending neural networks against adversarial attacks with certified guarantees.
Proper Network Interpretability Helps Adversarial Robustness in Classification
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to adversarial attacks.
Efficient Training of Robust and Verifiable Neural Networks
We propose that many common certified defenses can be viewed under a unified framework of regularization.
Visual Interpretability Alone Helps Adversarial Robustness
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability, and interpretability is itself susceptible to adversarial attacks.
CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
This motivates us to propose a general and efficient framework, CNN-Cert, that is capable of certifying robustness on general convolutional neural networks.
