Philemon Brakel

Recall Traces: Backtracking Models for Efficient Reinforcement Learning

Anirudh Goyal

Philemon Brakel

William Fedus

Soumye Singhal

Timothy P. Lillicrap

Sergey Levine

Hugo Larochelle

Yoshua Bengio

In many environments only a tiny subset of all states yield high reward. In these cases, few of the interactions with the environment provid… (see more)e a relevant learning signal. Hence, we may want to preferentially train on those high-reward states and the probable trajectories leading to them. To this end, we advocate for the use of a backtracking model that predicts the preceding states that terminate at a given high-reward state. We can train a model which, starting from a high value state (or one that is estimated to have high value), predicts and sample for which the (state, action)-tuples may have led to that high value state. These traces of (state, action) pairs, which we refer to as Recall Traces, sampled from this backtracking model starting from a high value state, are informative as they terminate in good states, and hence we can use these traces to improve a policy. We provide a variational interpretation for this idea and a practical algorithm in which the backtracking model samples from an approximate posterior distribution over trajectories which lead to large rewards. Our method improves the sample efficiency of both on- and off-policy RL algorithms across several environments and tasks.

2019-01-01

ICLR.cc/2019/Conference (poster)

openreview.net

Light Gated Recurrent Units for Speech Recognition

A field that has directly benefited from the recent advances in deep learning is automatic speech recognition (ASR). Despite the great achie… (see more)vements of the past decades, however, a natural and robust human–machine speech interaction still appears to be out of reach, especially in challenging environments characterized by significant noise and reverberation. To improve robustness, modern speech recognizers often employ acoustic models based on recurrent neural networks (RNNs) that are naturally able to exploit large time contexts and long-term speech modulations. It is thus of great interest to continue the study of proper techniques for improving the effectiveness of RNNs in processing speech signals. In this paper, we revise one of the most popular RNN models, namely, gated recurrent units (GRUs), and propose a simplified architecture that turned out to be very effective for ASR. The contribution of this work is twofold: First, we analyze the role played by the reset gate, showing that a significant redundancy with the update gate occurs. As a result, we propose to remove the former from the GRU design, leading to a more efficient and compact single-gate model. Second, we propose to replace hyperbolic tangent with rectified linear unit activations. This variation couples well with batch normalization and could help the model learn long-term dependencies without numerical issues. Results show that the proposed architecture, called light GRU, not only reduces the per-epoch training time by more than 30% over a standard GRU, but also consistently improves the recognition accuracy across different tasks, input features, noisy conditions, as well as across different ASR paradigms, ranging from standard DNN-HMM speech recognizers to end-to-end connectionist temporal classification models.

2018-04-01

IEEE Transactions on Emerging Topics in Computational Intelligence (published)

doi.org

arxiv.org

Learning Independent Features with Adversarial Nets for Non-linear ICA

Philemon Brakel

Yoshua Bengio

Reliable measures of statistical dependence could potentially be useful tools for learning independent features and performing tasks like so… (see more)urce separation using Independent Component Analysis (ICA). Unfortunately, many of such measures, like the mutual information, are hard to estimate and optimize directly. We propose to learn independent features with adversarial objectives (Goodfellow et al. 2014, Arjovsky et al. 2017) which optimize such measures implicitly. These objectives compare samples from the joint distribution and the product of the marginals without the need to compute any probability densities. We also propose two methods for obtaining samples from the product of the marginals using either a simple resampling trick or a separate parametric distribution. Our experiments show that this strategy can easily be applied to different types of model architectures and solve both linear and non-linear ICA problems.

2017-10-13

ArXiv (preprint)

openreview.net

An Actor-Critic Algorithm for Sequence Prediction

We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Curren… (see more)t log-likelihood training methods are limited by the discrepancy between their training and testing modes, as models must generate tokens conditioned on their previous guesses rather than the ground-truth tokens. We address this problem by introducing a textit{critic} network that is trained to predict the value of an output token, given the policy of an textit{actor} network. This results in a training procedure that is much closer to the test phase, and allows us to directly optimize for a task-specific score such as BLEU. Crucially, since we leverage these techniques in the supervised learning setting rather than the traditional RL setting, we condition the critic network on the ground-truth output. We show that our method leads to improved performance on both a synthetic task, and for German-English machine translation. Our analysis paves the way for such methods to be applied in natural language generation tasks, such as machine translation, caption generation, and dialogue modelling.

2017-01-01

ICLR.cc/2017/conference (poster)

openreview.net

Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic fe… (see more)atures for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs with Hidden Markov Models/Gaussian Mixture Models (HMMs/GMMs) have achieved the state-of-the-art in various benchmarks. 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. However, RNNs are computationally expensive and sometimes difficult to train. In this paper, inspired by the advantages of both CNNs and the CTC approach, we propose an end-to-end speech framework for sequence labeling, by combining hierarchical CNNs with CTC directly without recurrent connections. By evaluating the approach on the TIMIT phoneme recognition task, we show that the proposed model is not only computationally efficient, but also competitive with the existing baseline systems. Moreover, we argue that CNNs have the capability to model temporal correlations with appropriate context information.

2016-09-08

Interspeech 2016 (published)

doi.org

arxiv.org

Deconstructing the Ladder Network Architecture

Linxi Fan

The Ladder Network is a recent new approach to semi-supervised learning that turned out to be very successful. While showing impressive perf… (see more)ormance, the Ladder Network has many components intertwined, whose contributions are not obvious in such a complex architecture. This paper presents an extensive experimental investigation of variants of the Ladder Network in which we replaced or removed individual components to learn about their relative importance. For semi-supervised tasks, we conclude that the most important contribution is made by the lateral connections, followed by the application of noise, and the choice of what we refer to as the 'combinator function'. As the number of labeled training examples increases, the lateral connections and the reconstruction criterion become less important, with most of the generalization improvement coming from the injection of noise in each layer. Finally, we introduce a combinator function that reduces test error rates on Permutation-Invariant MNIST to 0.57% for the supervised setting, and to 0.97% and 1.0% for semi-supervised settings with 1000 and 100 labeled examples, respectively.

2016-06-11

Proceedings of The 33rd International Conference on Machine Learning (published)

proceedings.mlr.press

openreview.net

Task Loss Estimation for Structured Prediction

D. Serdyuk

Nan Rosemary Ke