Search Results for author:
Found 16 papers, 7 papers with code
Denoising Autoregressive Representation Learning
In this paper, we explore a new generative approach for learning visual representations.
Transformers for Supervised Online Continual Learning
Inspired by the in-context learning capabilities of transformers and their connection to meta-learning, we propose a method that leverages these strengths for online continual learning.
Practical Kernel Tests of Conditional Independence
We describe a data-efficient, kernel-based approach to statistical testing of conditional independence.
Evaluating Representations with Readout Model Switching
Although much of the success of Deep Learning builds on learning good representations, a rigorous method to evaluate their quality is lacking.
Investigating the role of model-based learning in exploration and transfer
Our results show that intrinsic exploration combined with environment models present a viable direction towards agents that are self-supervised and able to generalize to novel reward functions.
Efficient Conditionally Invariant Representation Learning
The procedure requires just a single ridge regression from $Y$ to kernelized features of $Z$, which can be done in advance.
Sequential Learning Of Neural Networks for Prequential MDL
In the prequential formulation of MDL, the objective is to minimize the cumulative next-step log-loss when sequentially going through the data and using previous observations for parameter estimation.
Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods
Self-supervised methods have achieved remarkable success in transfer learning, often achieving the same or better accuracy than supervised pre-training.
Procedural Generalization by Planning with Self-Supervised World Models
One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks.
Ranked #1 on
Meta-Learning
on ML10
(Meta-test success rate (zero-shot) metric)
Self-Supervised Learning with Kernel Dependence Maximization
We approach self-supervised learning of image representations from a statistical dependence perspective, proposing Self-Supervised Learning with the Hilbert-Schmidt Independence Criterion (SSL-HSIC).
Vector Quantized Models for Planning
Our key insight is to use discrete autoencoders to capture the multiple possible effects of an action in a stochastic environment.
Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decoder
In order to efficiently transmit and store speech signals, speech codecs create a minimally redundant representation of the input signal which is then decoded at the receiver with the best possible perceptual quality.
Representation Learning with Contrastive Predictive Coding
The key insight of our model is to learn such representations by predicting the future in latent space by using powerful autoregressive models.
Ranked #30 on
Semi-Supervised Image Classification
on ImageNet - 1% labeled data
(Top 5 Accuracy metric)
Representation Learning
Self-Supervised Image Classification
+1
DeepMind Control Suite
The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents.
Parallel WaveNet: Fast High-Fidelity Speech Synthesis
The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system.
Model-Free Episodic Control
State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance.
