paper-with-me

홈 › Papers

On Predictive Information Sub-optimality of RNNs

2019-09-25 · Zhe Dong, Deniz Oktay, Ben Poole, Alexander A. Alemi

Certain biological neurons demonstrate a remarkable capability to optimally compress the history of sensory inputs while being maximally informative about the future. In this work, we investigate if the same can be said of artificial neurons in recurrent neural networks (RNNs) trained with maximum likelihood. In experiments on two datasets, restorative Brownian motion and a hand-drawn sketch dataset, we find that RNNs are sub-optimal in the information plane. Instead of optimally compressing past information, they extract additional information that is not relevant for predicting the future. Overcoming this limitation may require alternative training procedures and architectures, or objectives beyond maximum likelihood estimation.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Information Plane

Similar Papers 제목 키워드 기반

On Predictive Information in RNNs

2019-10-21 · Zhe Dong, Deniz Oktay, Ben Poole, Alexander A. Alemi

Certain biological neurons demonstrate a remarkable capability to optimally compress the history of sensory inputs while being maximally informative about the future. In this work, we investigate if the same can be said …

Information Plane

Predictive State Recurrent Neural Networks

2017-05-25 · NeurIPS 2017 12 · Carlton Downey, Ahmed Hefny, Boyue Li, Byron Boots 외

We present a new model, Predictive State Recurrent Neural Networks (PSRNNs), for filtering and prediction in dynamical systems. PSRNNs draw on insights from both Recurrent Neural Networks (RNNs) and Predictive State Repr…

Tensor Decomposition

Global Optimality of Elman-type RNN in the Mean-Field Regime

2023-03-12 · Andrea Agazzi, Jianfeng Lu, Sayan Mukherjee

We analyze Elman-type Recurrent Reural Networks (RNNs) and their training in the mean-field regime. Specifically, we show convergence of gradient descent training dynamics of the RNN to the corresponding mean-field formu…

Vocal Bursts Type Prediction

Initialization matters: Orthogonal Predictive State Recurrent Neural Networks

2018-01-01 · ICLR 2018 1 · Krzysztof Choromanski, Carlton Downey, Byron Boots

Learning to predict complex time-series data is a fundamental challenge in a range of disciplines including Machine Learning, Robotics, and Natural Language Processing. Predictive State Recurrent Neural Networks (PSRNNs)…

regressionTime SeriesTime Series Analysis

Impact of leaky dynamics on predictive path integration accuracy in recurrent neural networks

2026-04-17 · Yanlin Zhang, Yan Zhang, Muhua Zheng, Kesheng Xu arxiv

Experimental evidence indicates that intrinsic temporal dynamics operating across multiple time scales are closely associated with the emergence of periodic spatial activity of increasing complexity. However, how informa…