paper-with-me

홈 › Papers

Internal representation dynamics and geometry in recurrent neural networks

2020-01-09 · Stefan Horoi, Guillaume Lajoie, Guy Wolf

The efficiency of recurrent neural networks (RNNs) in dealing with sequential data has long been established. However, unlike deep, and convolution networks where we can attribute the recognition of a certain feature to every layer, it is unclear what "sub-task" a single recurrent step or layer accomplishes. Our work seeks to shed light onto how a vanilla RNN implements a simple classification task by analysing the dynamics of the network and the geometric properties of its hidden states. We find that early internal representations are evocative of the real labels of the data but this information is not directly accessible to the output layer. Furthermore the network's dynamics and the sequence length are both critical to correct classifications even when there is no additional task relevant information provided.

📄 PDF Abstract BibTeX arXiv:2001.03255

Code (0)

등록된 구현이 없습니다.

Tasks

Attribute

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Embedding of Low-Dimensional Sensory Dynamics in Recurrent Networks: Implications for the Geometry of Neural Representation

2026-01-26 · Vikas N. O'Reilly-Shah, Alessandro Maria Selvitella arxiv

Neural population activity in sensory cortex is organized on low-dimensional manifolds, but why such manifolds arise and what determines their geometry remain unclear. We model cortical populations as recurrent circuits …

Interpretable statistical representations of neural population dynamics and geometry

2023-04-06 · Adam Gosztolai, Robert L. Peach, Alexis Arnaudon, Mauricio Barahona 외

The dynamics of neuron populations commonly evolve on low-dimensional manifolds. Thus, we need methods that learn the dynamical processes over neural manifolds to infer interpretable and consistent latent representations…

BenchmarkingDecision MakingInductive BiasRepresentation Learning

Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis

2023-06-16 · NeurIPS 2023 11 · Mitchell Ostrow, Adam Eisen, Leo Kozachkov, Ila Fiete

How can we tell whether two neural networks utilize the same internal processes for a particular computation? This question is pertinent for multiple subfields of neuroscience and machine learning, including neuroAI, mec…

Relative Geometry of Neural Forecasters: Linking Accuracy and Alignment in Learned Latent Geometry

2026-02-17 · Deniz Kucukahmetler, Maximilian Jean Hemmann, Julian Mosig von Aehrenfeld, Maximilian Amthor 외 arxiv

Neural networks can accurately forecast complex dynamical systems, yet how they internally represent underlying latent geometry remains poorly understood. We study neural forecasters through the lens of representational …

Neural Co-state Policies: Structuring Hidden States in Recurrent Reinforcement Learning

2026-05-06 · David Leeftink, Max Hinne, Marcel van Gerven arxiv

A key capability of intelligent agents is operating under partial observability: reasoning and acting effectively despite missing or incomplete state observations. While recurrent (memory-based) policies learned via rein…

Reinforcement LearningContinuous Control