Search Results for author:
Found 44 papers, 22 papers with code
Leveraging the Third Dimension in Contrastive Learning
We evaluate these two approaches on three different SSL methods -- BYOL, SimSiam, and SwAV -- using ImageNette (10 class subset of ImageNet), ImageNet-100 and ImageNet-1k datasets.
Representation Learning in Deep RL via Discrete Information Bottleneck
Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations.
Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks.
Neural Active Learning on Heteroskedastic Distributions
To this end, we demonstrate the catastrophic failure of these active learning algorithms on heteroskedastic distributions and propose a fine-tuning-based approach to mitigate these failures.
Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning
Goal-conditioned reinforcement learning (RL) is a promising direction for training agents that are capable of solving multiple tasks and reach a diverse set of objectives.
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
We find that contemporary representation learning techniques can fail on datasets where the noise is a complex and time dependent process, which is prevalent in practical applications.
CNT (Conditioning on Noisy Targets): A new Algorithm for Leveraging Top-Down Feedback
We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT).
Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models
In many sequential decision-making tasks, the agent is not able to model the full complexity of the world, which consists of multitudes of relevant and irrelevant information.
Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning
A slow stream that is recurrent in nature aims to learn a specialized and compressed representation, by forcing chunks of $K$ time steps into a single representation which is divided into multiple vectors.
Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization
Vector Quantization (VQ) is a method for discretizing latent representations and has become a major part of the deep learning toolkit.
Discrete-Valued Neural Communication
Deep learning has advanced from fully connected architectures to structured models organized into components, e. g., the transformer composed of positional elements, modular architectures divided into slots, and graph neural nets made up of nodes.
Predicting the Ordering of Characters in Japanese Historical Documents
A major research project has been to make these historical documents accessible and understandable.
Coordination Among Neural Modules Through a Shared Global Workspace
We explore the use of such a communication channel in the context of deep learning for modeling the structure of complex environments.
A Brief Introduction to Generative Models
We overview how generative modeling can be defined mathematically as trying to make an estimating distribution the same as an unknown ground truth distribution.
Transformers with Competitive Ensembles of Independent Mechanisms
In this work we explore a way in which the Transformer architecture is deficient: it represents each position with a large monolithic hidden representation and a single set of parameters which are applied over the entire hidden representation.
Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments
To use a video game as an illustration, two enemies of the same type will share schemata but will have separate object files to encode their distinct state (e. g., health, position).
Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
Feed-forward neural networks consist of a sequence of layers, in which each layer performs some processing on the information from the previous layer.
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
To effectively utilize the wealth of potential top-down information available, and to prevent the cacophony of intermixed signals in a bidirectional architecture, mechanisms are needed to restrict information flow.
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
To use a video game as an illustration, two enemies of the same type will share schemata but will have separate object files to encode their distinct state (e. g., health, position).
Jigsaw-VAE: Towards Balancing Features in Variational Autoencoders
The latent variables learned by VAEs have seen considerable interest as an unsupervised way of extracting features, which can then be used for downstream tasks.
KaoKore: A Pre-modern Japanese Art Facial Expression Dataset
From classifying handwritten digits to generating strings of text, the datasets which have received long-time focus from the machine learning community vary greatly in their subject matter.
SketchTransfer: A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks
In this work we focus on their ability to have invariance towards the presence or absence of details.
KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning
However, following a change to the Japanese writing system in 1900, Kuzushiji has not been included in regular school curricula.
GraphMix: Improved Training of GNNs for Semi-Supervised Learning
We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization.
Ranked #1 on
Node Classification
on Bitcoin-Alpha
GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning
We present GraphMix, a regularization technique for Graph Neural Network based semi-supervised object classification, leveraging the recent advances in the regularization of classical deep neural networks.
Recurrent Independent Mechanisms
Learning modular structures which reflect the dynamics of the environment can lead to better generalization and robustness to changes which only affect a few of the underlying causes.
Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy
Adversarial robustness has become a central goal in deep learning, both in the theory and the practice.
State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Machine learning promises methods that generalize well from finite labeled data.
Manifold Mixup: Learning Better Representations by Interpolating Hidden States
Because the hidden states are learned, this has an important effect of encouraging the hidden states for a class to be concentrated in such a way so that interpolations within the same class or between two different classes do not intersect with the real data points from other classes.
Adversarial Mixup Resynthesizers
In this paper, we explore new approaches to combining information encoded within the learned representations of autoencoders.
Interpolation Consistency Training for Semi-Supervised Learning
We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm.
On Adversarial Mixup Resynthesis
In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders.
Deep Learning for Classical Japanese Literature
Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks.
Ranked #4 on
Image Classification
on Kuzushiji-MNIST
(Error metric)
Manifold Mixup: Better Representations by Interpolating Hidden States
Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples.
Ranked #19 on
Image Classification
on OmniBenchmark
Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations
Deep networks have achieved impressive results across a variety of important tasks.
Learning Generative Models with Locally Disentangled Latent Factors
One of the most successful techniques in generative models has been decomposing a complicated generation task into a series of simpler generation tasks.
GibbsNet: Iterative Adversarial Inference for Deep Graphical Models
Directed latent variable models that formulate the joint distribution as $p(x, z) = p(z) p(x \mid z)$ have the advantage of fast and exact sampling.
ACtuAL: Actor-Critic Under Adversarial Learning
This makes it fundamentally difficult to train GANs with discrete data, as generation in this case typically involves a non-differentiable function.
Professor Forcing: A New Algorithm for Training Recurrent Networks
We introduce the Professor Forcing algorithm, which uses adversarial domain adaptation to encourage the dynamics of the recurrent network to be the same when training the network and when sampling from the network over multiple time steps.
Adversarially Learned Inference
We introduce the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process.
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.
Discriminative Regularization for Generative Models
We propose to take advantage of this by using the representations from discriminative classifiers to augment the objective function corresponding to a generative model.
Variance Reduction in SGD by Distributed Importance Sampling
This leads the model to update using an unbiased estimate of the gradient which also has minimum variance when the sampling proposal is proportional to the L2-norm of the gradient.
