paper-with-me

Papers

DeepSITH: Efficient Learning via Decomposition of What and When Across Time Scales

2021-04-09 · NeurIPS 2021 12 · Brandon Jacques, Zoran Tiganj, Marc W. Howard, Per B. Sederberg

Extracting temporal relationships over a range of scales is a hallmark of human perception and cognition -- and thus it is a critical feature of machine learning applied to real-world problems. Neural networks are either plagued by the exploding/vanishing gradient problem in recurrent neural networks (RNNs) or must adjust their parameters to learn the relevant time scales (e.g., in LSTMs). This paper introduces DeepSITH, a network comprising biologically-inspired Scale-Invariant Temporal History (SITH) modules in series with dense connections between layers. SITH modules respond to their inputs with a geometrically-spaced set of time constants, enabling the DeepSITH network to learn problems along a continuum of time-scales. We compare DeepSITH to LSTMs and other recent RNNs on several time series prediction and decoding tasks. DeepSITH achieves state-of-the-art performance on these problems.

📄 PDF Abstract BibTeX arXiv:2104.04646

Code (1)

compmem/deepsith 공식 구현 pytorch

Tasks

Time SeriesTime Series AnalysisTime Series Prediction

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Affordance-First Decomposition for Continual Learning in Video-Language Understanding

2025-11-30 · Mengzhu Xu, Hanzhi Liu, Ningkang Peng, Qianyu Chen 외 arxiv

Continual learning for video--language understanding is increasingly important as models face non-stationary data, domains, and query styles, yet prevailing solutions blur what should stay stable versus what should adapt…

Continual Learning

How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?

2023-05-09 · Jetze T. Schuurmans, Kim Batselier, Julian F. P. Kooij

Tensor decompositions have been successfully applied to compress neural networks. The compression algorithms using tensor decompositions commonly minimize the approximation error on the weights. Recent work assumes the a…

Neural Network CompressionTensor Decomposition

Fast and Accurate Dual-Way Streaming PARAFAC2 for Irregular Tensors -- Algorithm and Application

2023-05-28 · Jun-Gi Jang, Jeongyoung Lee, Yong-chan Park, U Kang

How can we efficiently and accurately analyze an irregular tensor in a dual-way streaming setting where the sizes of two dimensions of the tensor increase over time? What types of anomalies are there in the dual-way stre…

Profit and loss decomposition in continuous time and approximations

2022-12-13 · Gero Junike, Hauke Stier, Marcus C. Christiansen

Financial institutions and insurance companies that analyze the evolution and sources of profits and losses often look at risk factors only at discrete reporting dates, ignoring the detailed paths. Continuous-time decomp…

Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP

2026-05-15 · Igor Bogdanov, Chung-Horng Lung, Thomas Kunz, Jie Gao 외 arxiv

Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reasons, and (3) how tasks are decomposed acro…