Search Results for author:
Found 11 papers, 4 papers with code
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.
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
A central goal for AI and causality is thus the joint discovery of abstract representations and causal structure.
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.
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.
ARHNet - Leveraging Community Interaction for Detection of Religious Hate Speech in Arabic
The rapid widespread of social media has lead to some undesirable consequences like the rapid increase of hateful content and offensive language.
Neural Production Systems: Learning Rule-Governed Visual Dynamics
First, GNNs do not predispose interactions to be sparse, as relationships among independent entities are likely to be.
Augmenting NLP models using Latent Feature Interpolations
Models with a large number of parameters are prone to over-fitting and often fail to capture the underlying input distribution.
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.
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).
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.
Cycle Consistency Driven Object Discovery
To tackle the second limitation, we apply the learned object-centric representations from the proposed method to two downstream reinforcement learning tasks, demonstrating considerable performance enhancements compared to conventional slot-based and monolithic representation learning methods.
