Higher-Order Spatial Information for Self-Supervised Place Cell Learning
Mammals navigate novel environments and exhibit resilience to sparse environmental sensory cues via place and grid cells, which encode position in space. While the efficiency of grid cell coding has been extensively studied, the computational role of place cells is less well understood. This gap arises partially because spatial information measures have, until now, been limited to single place cells. We derive and implement a higher-order spatial information measure, allowing for the study of the emergence of multiple place cells in a self-supervised manner. We show that emergent place cells have many desirable features, including high-accuracy spatial decoding. This is the first work in which higher-order spatial information measures that depend solely on place cells' firing rates have been derived and which focuses on the emergence of multiple place cells via self-supervised learning. By quantifying the spatial information of multiple place cells, we enhance our understanding of place cell formation and capabilities in recurrent neural networks, thereby improving the potential navigation capabilities of artificial systems in novel environments without objective location information.
Code (0)
등록된 구현이 없습니다.
Tasks
NavigateSelf-Supervised LearningSimilar Papers 제목 키워드 기반
ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning
This paper presents a new self-supervised video representation learning framework, ARVideo, which autoregressively predicts the next video token in a tailored sequence order. Two key designs are included. First, we organ…
GPURepresentation LearningHeterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations
Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper p…
Contrastive LearningData AugmentationRepresentation LearningContinual Learning of Conjugated Visual Representations through Higher-order Motion Flows
Learning with neural networks from a continuous stream of visual information presents several challenges due to the non-i.i.d. nature of the data. However, it also offers novel opportunities to develop representations th…
Continual LearningOptical Flow EstimationIncorporating Higher-order Structural Information for Graph Clustering
Clustering holds profound significance in data mining. In recent years, graph convolutional network (GCN) has emerged as a powerful tool for deep clustering, integrating both graph structural information and node attribu…
ClusteringDeep ClusteringGraph ClusteringZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding
State Space models (SSMs) such as PointMamba enable efficient feature extraction for point cloud self-supervised learning with linear complexity, outperforming Transformers in computational efficiency. However, existing …
Computational EfficiencyMambaSelf-Supervised LearningState Space Models