paper-with-me

홈 › Papers

Interpreting neural computations by examining intrinsic and embedding dimensionality of neural activity

2021-07-08 · Mehrdad Jazayeri, Srdjan Ostojic

The ongoing exponential rise in recording capacity calls for new approaches for analysing and interpreting neural data. Effective dimensionality has emerged as an important property of neural activity across populations of neurons, yet different studies rely on different definitions and interpretations of this quantity. Here we focus on intrinsic and embedding dimensionality, and discuss how they might reveal computational principles from data. Reviewing recent works, we propose that the intrinsic dimensionality reflects information about the latent variables encoded in collective activity, while embedding dimensionality reveals the manner in which this information is processed. We conclude by highlighting the role of network models as an ideal substrate for testing more specifically various hypotheses on the computational principles reflected through intrinsic and embedding dimensionality.

📄 PDF Abstract BibTeX arXiv:2107.04084

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LORE: Jointly Learning the Intrinsic Dimensionality and Relative Similarity Structure From Ordinal Data

2026-02-04 · Vivek Anand, Alec Helbling, Mark A. Davenport, Gordon J. Berman 외 arxiv

Learning the intrinsic dimensionality of subjective perceptual spaces such as taste, smell, or aesthetics from ordinal data is a challenging problem. We introduce LORE (Low Rank Ordinal Embedding), a scalable framework t…

The Role of Context Types and Dimensionality in Learning Word Embeddings

2016-01-05 · NAACL 2016 6 · Oren Melamud, David McClosky, Siddharth Patwardhan, Mohit Bansal

We provide the first extensive evaluation of how using different types of context to learn skip-gram word embeddings affects performance on a wide range of intrinsic and extrinsic NLP tasks. Our results suggest that whil…

Learning Word EmbeddingsWord Embeddings

Local Intrinsic Dimensionality for Dynamic Graph Embeddings

2024-11-25 · Dušica Knežević, Miloš Savić, Miloš Radovanović

The notion of local intrinsic dimensionality (LID) has important theoretical implications and practical applications in the fields of data mining and machine learning. Recent research efforts indicate that LID measures d…

Dynamic graph embeddingGraph Embedding

Local Intrinsic Dimensionality Measures for Graphs, with Applications to Graph Embeddings

2022-08-25 · Miloš Savić, Vladimir Kurbalija, Miloš Radovanović

The notion of local intrinsic dimensionality (LID) is an important advancement in data dimensionality analysis, with applications in data mining, machine learning and similarity search problems. Existing distance-based L…

Graph Embedding

PCA-Based Out-of-Sample Extension for Dimensionality Reduction

2015-11-03 · Yariv Aizenbud, Amit Bermanis, Amir Averbuch

Dimensionality reduction methods are very common in the field of high dimensional data analysis. Typically, algorithms for dimensionality reduction are computationally expensive. Therefore, their applications for the ana…

Dimensionality Reduction