Search Results for author:
Found 16 papers, 7 papers with code
Theano: A Python framework for fast computation of mathematical expressions
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
Gradient Starvation: A Learning Proclivity in Neural Networks
We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
We propose zoneout, a novel method for regularizing RNNs.
Simple data balancing achieves competitive worst-group-accuracy
We study the problem of learning classifiers that perform well across (known or unknown) groups of data.
Ranked #1 on
Out-of-Distribution Generalization
on UrbanCars
Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks
Meanwhile, Connectionist Temporal Classification (CTC) with Recurrent Neural Networks (RNNs), which is proposed for labeling unsegmented sequences, makes it feasible to train an end-to-end speech recognition system instead of hybrid settings.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Negative Momentum for Improved Game Dynamics
Games generalize the single-objective optimization paradigm by introducing different objective functions for different players.
Multi-scale Feature Learning Dynamics: Insights for Double Descent
A key challenge in building theoretical foundations for deep learning is the complex optimization dynamics of neural networks, resulting from the high-dimensional interactions between the large number of network parameters.
Deconstructing the Ladder Network Architecture
Although the empirical results are impressive, the Ladder Network has many components intertwined, whose contributions are not obvious in such a complex architecture.
Sequence Modeling using Gated Recurrent Neural Networks
In this paper, we have used Recurrent Neural Networks to capture and model human motion data and generate motions by prediction of the next immediate data point at each time-step.
Distinction between features extracted using deep belief networks
Data representation is an important pre-processing step in many machine learning algorithms.
Deep Belief Networks for Image Denoising
In this paper, we propose a novel method for image denoising which relies on the DBNs' ability in feature representation.
On the Learning Dynamics of Deep Neural Networks
While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely misunderstood.
Convergence Properties of Deep Neural Networks on Separable Data
While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely misunderstood.
Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok
In essence, by studying the learning curve of the first few epochs, we show that one can predict whether grokking will occur later on.
Discovering environments with XRM
Successful out-of-distribution generalization requires environment annotations.
Feedback-guided Data Synthesis for Imbalanced Classification
In this work, we introduce a framework for augmenting static datasets with useful synthetic samples, which leverages one-shot feedback from the classifier to drive the sampling of the generative model.
