Search Results for author:
Found 21 papers, 9 papers with code
Fast Simultaneous Training of Generalized Linear Models (FaSTGLZ)
We present an efficient algorithm for simultaneously training sparse generalized linear models across many related problems, which may arise from bootstrapping, cross-validation and nonparametric permutation testing.
Discovering Hidden Factors of Variation in Deep Networks
Deep learning has enjoyed a great deal of success because of its ability to learn useful features for tasks such as classification.
Discovering Hidden Factors of Variation in DeepNetworks
Deep learning has enjoyed a great deal of success because of its ability to learnuseful features for tasks such as classification.
Emergence of foveal image sampling from learning to attend in visual scenes
We describe a neural attention model with a learnable retinal sampling lattice.
Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich.
Generalization Challenges for Neural Architectures in Audio Source Separation
Recent work has shown that recurrent neural networks can be trained to separate individual speakers in a sound mixture with high fidelity.
Meta-Learning Update Rules for Unsupervised Representation Learning
Specifically, we target semi-supervised classification performance, and we meta-learn an algorithm -- an unsupervised weight update rule -- that produces representations useful for this task.
Superposition of many models into one
We present a method for storing multiple models within a single set of parameters.
Learning Unsupervised Learning Rules
Here, our desired task (meta-objective) is the performance of the representation on semi-supervised classification, and we meta-learn an algorithm -- an unsupervised weight update rule -- that produces representations that perform well under this meta-objective.
Hope For The Best But Prepare For The Worst: Cautious Adaptation In RL Agents
We study the problem of safe adaptation: given a model trained on a variety of past experiences for some task, can this model learn to perform that task in a new situation while avoiding catastrophic failure?
Word Embedding Visualization Via Dictionary Learning
Co-occurrence statistics based word embedding techniques have proved to be very useful in extracting the semantic and syntactic representation of words as low dimensional continuous vectors.
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous, imperiling the RL agent, other agents, and the environment.
The Low-Rank Simplicity Bias in Deep Networks
We show empirically that our claim holds true on finite width linear and non-linear models on practical learning paradigms and show that on natural data, these are often the solutions that generalize well.
Compact and Optimal Deep Learning with Recurrent Parameter Generators
We propose a drastically different approach to compact and optimal deep learning: We decouple the Degrees of freedom (DoF) and the actual number of parameters of a model, optimize a small DoF with predefined random linear constraints for a large model of arbitrary architecture, in one-stage end-to-end learning.
Ranked #97 on
Image Classification
on ObjectNet
(using extra training data)
Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations
In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge.
Equivariant Contrastive Learning
In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge.
Meta-Learning and Self-Supervised Pretraining for Real World Image Translation
In recent years, emerging fields such as meta-learning or self-supervised learning have been closing the gap between proof-of-concept results and real-life applications of machine learning by extending deep-learning to the semi-supervised and few-shot domains.
System identification of neural systems: If we got it right, would we know?
The networks are compared to recordings of biological neurons, and good performance in reproducing neural responses is considered to support the model's validity.
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
We identify the factors that contribute to this issue, including the codebook gradient sparsity and the asymmetric nature of the commitment loss, which leads to misaligned code-vector assignments.
How to guess a gradient
We study how to narrow the gap in optimization performance between methods that calculate exact gradients and those that use directional derivatives.
Training Neural Networks from Scratch with Parallel Low-Rank Adapters
The scalability of deep learning models is fundamentally limited by computing resources, memory, and communication.
