Search Results for author:
Found 39 papers, 15 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.
Twin Networks: Matching the Future for Sequence Generation
We propose a simple technique for encouraging generative RNNs to plan ahead.
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
We propose zoneout, a novel method for regularizing RNNs.
Task Loss Estimation for Sequence Prediction
Our idea is that this score can be interpreted as an estimate of the task loss, and that the estimation error may be used as a consistent surrogate loss.
Learning Neural Causal Models from Unknown Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.
Learning Neural Causal Models with Active Interventions
Discovering causal structures from data is a challenging inference problem of fundamental importance in all areas of science.
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.
Z-Forcing: Training Stochastic Recurrent Networks
Stochastic recurrent models have been successful in capturing the variability observed in natural sequential data such as speech.
Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net
The energy function is then modified so the model and data distributions match, with no guarantee on the number of steps required for the Markov chain to converge.
Ethical Challenges in Data-Driven Dialogue Systems
The use of dialogue systems as a medium for human-machine interaction is an increasingly prevalent paradigm.
Towards Understanding How Machines Can Learn Causal Overhypotheses
Recent work in machine learning and cognitive science has suggested that understanding causal information is essential to the development of intelligence.
h-detach: Modifying the LSTM Gradient Towards Better Optimization
This problem becomes more evident in tasks where the information needed to correctly solve them exist over long time scales, because EVGP prevents important gradient components from being back-propagated adequately over a large number of steps.
Cascading Bandits for Large-Scale Recommendation Problems
In this work, we study cascading bandits, an online learning variant of the cascade model where the goal is to recommend $K$ most attractive items from a large set of $L$ candidate items.
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.
On the Convergence of Continuous Constrained Optimization for Structure Learning
Recently, structure learning of directed acyclic graphs (DAGs) has been formulated as a continuous optimization problem by leveraging an algebraic characterization of acyclicity.
Focused Hierarchical RNNs for Conditional Sequence Processing
We evaluate this method on several types of tasks with different attributes.
Ranked #3 on
Open-Domain Question Answering
on SearchQA
(Unigram Acc metric)
A Deep Reinforcement Learning Chatbot (Short Version)
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition.
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.
Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks
A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagate credit information backwards through every single step of the forward computation.
A Deep Reinforcement Learning Chatbot
By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble.
Transferring Knowledge from a RNN to a DNN
The small DNN trained on the soft RNN alignments achieved a 3. 93 WER on the Wall Street Journal (WSJ) eval92 task compared to a baseline 4. 54 WER or more than 13% relative improvement.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding
We consider the hypothesis that such memory associations between past and present could be used for credit assignment through arbitrarily long sequences, propagating the credit assigned to the current state to the associated past state.
Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding
We consider the hypothesis that such memory associations between past and present could be used for credit assignment through arbitrarily long sequences, propagating the credit assigned to the current state to the associated past state.
Modeling the Long Term Future in Model-Based Reinforcement Learning
This paper focuses on building a model that reasons about the long-term future and demonstrates how to use this for efficient planning and exploration.
Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future
This paper focuses on building a model that reasons about the long-term future and demonstrates how to use this for efficient planning and exploration.
Causally Correct Partial Models for Reinforcement Learning
In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions.
Amortized learning of neural causal representations
The CRN represent causal models using continuous representations and hence could scale much better with the number of variables.
Dependency Structure Discovery from Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.
Meta Attention Networks: Meta-Learning Attention to Modulate Information Between Recurrent Independent Mechanisms
Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution.
Towards Causal Representation Learning
The two fields of machine learning and graphical causality arose and developed separately.
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.
Fast and Slow Learning of Recurrent Independent Mechanisms
To study these ideas, we propose a particular training framework in which we assume that the pieces of knowledge an agent needs and its reward function are stationary and can be re-used across tasks.
Retrieval-Augmented Reinforcement Learning
In this paper we explore an alternative paradigm in which we train a network to map a dataset of past experiences to optimal behavior.
Learning Causal Overhypotheses through Exploration in Children and Computational Models
Despite recent progress in reinforcement learning (RL), RL algorithms for exploration still remain an active area of research.
Learning to Induce Causal Structure
The fundamental challenge in causal induction is to infer the underlying graph structure given observational and/or interventional data.
On the Generalization and Adaption Performance of Causal Models
Our analysis shows that the modular neural causal models outperform other models on both zero and few-shot adaptation in low data regimes and offer robust generalization.
Learning Latent Structural Causal Models
For linear Gaussian additive noise SCMs, we present a tractable approximate inference method which performs joint inference over the causal variables, structure and parameters of the latent SCM from random, known interventions.
Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration
To generalize across tasks, an agent should acquire knowledge from past tasks that facilitate adaptation and exploration in future tasks.
DiscoGen: Learning to Discover Gene Regulatory Networks
To accurately identify GRNs, perturbational data is required.
