paper-with-me

Papers

Surprisal-Driven Zoneout

2016-10-24 · Kamil Rocki, Tomasz Kornuta, Tegan Maharaj

We propose a novel method of regularization for recurrent neural networks called suprisal-driven zoneout. In this method, states zoneout (maintain their previous value rather than updating), when the suprisal (discrepancy between the last state's prediction and target) is small. Thus regularization is adaptive and input-driven on a per-neuron basis. We demonstrate the effectiveness of this idea by achieving state-of-the-art bits per character of 1.31 on the Hutter Prize Wikipedia dataset, significantly reducing the gap to the best known highly-engineered compression methods.

📄 PDF Abstract BibTeX arXiv:1610.07675

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Zoneout Zoneout is a method for regularizing RNNs. At each timestep, zoneout stochastically forces some…

Similar Papers 제목 키워드 기반

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

2016-06-03 · David Krueger, Tegan Maharaj, János Kramár, Mohammad Pezeshki 외

We propose zoneout, a novel method for regularizing RNNs. At each timestep, zoneout stochastically forces some hidden units to maintain their previous values. Like dropout, zoneout uses random noise to train a pseudo-ens…

Language Modelling

Modeling intra-textual variation with entropy and surprisal: topical vs. stylistic patterns

2017-08-01 · WS 2017 8 · Stefania Degaetano-Ortlieb, Elke Teich

We present a data-driven approach to investigate intra-textual variation by combining entropy and surprisal. With this approach we detect linguistic variation based on phrasal lexico-grammatical patterns across sections …

Articles

Surprisal-Driven Feedback in Recurrent Networks

2016-08-22 · Kamil M Rocki

Recurrent neural nets are widely used for predicting temporal data. Their inherent deep feedforward structure allows learning complex sequential patterns. It is believed that top-down feedback might be an important missi…

Towards a Similarity-adjusted Surprisal Theory

2024-10-23 · Clara Meister, Mario Giulianelli, Tiago Pimentel

Surprisal theory posits that the cognitive effort required to comprehend a word is determined by its contextual predictability, quantified as surprisal. Traditionally, surprisal theory treats words as distinct entities, …

Diversity

MIME: Mutual Information Minimisation Exploration

2020-01-16 · Haitao Xu, Brendan McCane, Lech Szymanski, Craig Atkinson

We show that reinforcement learning agents that learn by surprise (surprisal) get stuck at abrupt environmental transition boundaries because these transitions are difficult to learn. We propose a counter-intuitive solut…

Montezuma's Revengereinforcement-learningReinforcement LearningReinforcement Learning (RL)