Sparse coding with an overcomplete basis set: A strategy employed by V1?
1997/12/01 by Bruno A. Olshausen, David J. Field · 61 citations
Biochemistry, Genetics and Molecular Biology · Neuroscience · #Advanced Fluorescence Microscopy Techniques #Neural dynamics and brain function #Visual perception and processing mechanisms
paper · doi:10.1016/s0042-6989(97)00169-7
openalex publication_date 1997/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29
Citations
Cited by
- Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
- Toward a mechanistic understanding of inference in visual cortex and diffusion models
- Convergent Evolution: How Different Language Models Learn Similar Number Representations
- A Network of Biologically Inspired Rectified Spectral Units (ReSUs) Learns Hierarchical Features Without Error Backpropagation
- Base Models Know How to Reason, Thinking Models Learn When
- Interpreting the linear structure of vision-language model embedding spaces
- Voltage imaging as a window into neural computation
- Towards Isolated Interventions via Almost Orthogonal Features in Language Models
- Generative Giants, Retrieval Weaklings: Why do Multimodal Large Language Models Fail at Multimodal Retrieval?
- From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
- SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination
- Generalized Interlacing Families: New Error Bounds for CUR Matrix Decompositions
- Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
- FoldSAE: Learning to Steer Protein Folding Through Sparse Representations
- Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks
- Representation learning in cerebellum-like structures
- Accelerated primal dual fixed point algorithm
- Use and usability: concepts of representation in philosophy, neuroscience, cognitive science, and computer science
- IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning
- Semantic representations emerge in biologically inspired ensembles of cross-supervising neural networks
- Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders
- A Unified Probabilistic Framework for Dictionary Learning with Parsimonious Activation
- Concept-SAE: Active Causal Probing of Visual Model Behavior
- Distributed Specialization: Rare-Token Neurons in Large Language Models
- ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders
- SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
- Probabilistic Performance-Pattern Decomposition (PPPD): analysis framework and applications to stochastic mechanical systems
- Evolution of Concepts in Language Model Pre-Training
- A Novel Differential Feature Learning for Effective Hallucination Detection and Classification
- Structured Dictionary Learning for Classification
- Transformational Sparse Coding
- Variational Autoencoder with Learned Latent Structure
- The implications of perception as probabilistic inference for correlated neural variability during behavior
- Sparse Autoencoder Neural Operators: Model Recovery in Function Spaces
- Learning Latent Space Energy-Based Prior Model
- On sources to variabilities of simple cells in the primary visual cortex: A principled theory for the interaction between geometric image transformations and receptive field responses
- Correlates of Image Memorability in Vision Encoders: Activations, Attention Entropy, Patch Uniformity and Autoencoder Losses
- Metabolic cost as an organizing principle for cooperative learning
- Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
- P-SIF: Document Embeddings Using Partition Averaging
- Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving
- Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700\n Robot Hours
- Deep Predictive Learning: A Comprehensive Model of Three Visual Streams
- Neuro-inspired Ensemble-to-Ensemble Communication Primitives for Sparse and Efficient ANNs
- Uncovering Emergent Physics Representations Learned In-Context by Large Language Models
- Towards Understanding 3D Vision: the Role of Gaussian Curvature
- Probing the Representational Power of Sparse Autoencoders in Vision Models
- Generalization and Expressivity for Deep Nets
- Anomaly-Sensitive Dictionary Learning for Unsupervised Diagnostics of Solid Media
- A Parametric Bi-Directional Curvature-Based Framework for Image Artifact Classification and Quantification
- Early Methods for Detecting Adversarial Images
- Quality Versus Sparsity in Image Recovery by Dictionary Learning Using Iterative Shrinkage
- Multiscale Dictionary Learning: Non-Asymptotic Bounds and Robustness
- Making Good on LSTMs' Unfulfilled Promise
- EB-gMCR: Energy-Based Generative Modeling for Signal Unmixing and Multivariate Curve Resolution
- Elastic regularization in restricted Boltzmann machines: Dealing with p≫ N
- Deep Double Sparsity Encoder: Learning to Sparsify Not Only Features But Also Parameters
- Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration
- A Sparse Coding Interpretation of Neural Networks and Theoretical Implications
- Sparse, complex-valued representations of natural sounds learned with phase and amplitude continuity priors
- The Deterministic Information Bottleneck