On Invariance and Selectivity in Representation Learning
Explore this paper's citation graph
Summary
This paper builds on the idea that data representation, which are learned in an unsupervised manner, can be key to solve the problem of learning "good" data representation which can lower the need of labeled data in machine learning.
- Type
- article
- Published
- 2015-03-19
- Cited by
- 110
- References
- 43
- Access
- Open access
- OpenAlex
- https://openalex.org/W1635792279
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:10906794
Keywords
Representation (politics), MAGIC (telescope), Sensory system, Computer science, Invariant (physics)
References
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
- Hilbertian Metrics and Positive Definite Kernels on Probability Measures
- Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors
- Reproducing kernel Hilbert spaces in probability and statistics
- RECEPTIVE FIELDS AND FUNCTIONAL ARCHITECTURE IN TWO NONSTRIATE VISUAL AREAS (18 AND 19) OF THE CAT.
- Efficient Sketches for Earth-Mover Distance, with Applications
- On the theory of reproducing kernel Hilbert spaces
- Statistical Decision Theory and Bayesian Analysis, Second Edition
- Group Invariant Scattering
- On the mathematical foundations of learning
- Invariant kernel functions for pattern analysis and machine learning
- Some Theorems on Distribution Functions
- Learning Deep Architectures for AI
- The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex
- Efficient Additive Kernels via Explicit Feature Maps
- Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
- Support Theorems for the Radon Transform and Cramér-Wold Theorems
- Distance Metric Learning with Application to Clustering with Side-Information
- Receptive fields and functional architecture of monkey striate cortex
- Hilbert Space Embeddings and Metrics on Probability Measures
Cited by
- The dynamics of invariant object and action recognition in the human visual system
- A Probabilistic Theory of Deep Learning
- GSNs : Generative Stochastic Networks
- Why neurons mix: high dimensionality for higher cognition.
- Group Equivariant Convolutional Networks
- Representation Learning in Sensory Cortex: A Theory
- Notes on Hierarchical Splines, DCLNs and i-theory
- A theoretical framework for deep transfer learning
- An Empirical Evaluation of Current Convolutional Architectures’ Ability to Manage Nuisance Location and Scale Variability
- Discriminative template learning in group-convolutional networks for invariant speech representations
- View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation
- Visual-Inertial Scene Representations
- Learning Text Similarity with Siamese Recurrent Networks
- A Biologically Inspired Framework for Visual Information Processing and an Application on Modeling Bottom-Up Visual Attention
- Joint Learning of Speaker and Phonetic Similarities with Siamese Networks
- Information Dropout: learning optimal representations through noise
- Automatic Discoveries of Physical and Semantic Concepts via Association Priors of Neuron Groups
- Emergence of Selective Invariance in Hierarchical Feed Forward Networks
- Robust image classification: analysis and applications
- On the effect of pooling on the geometry of representations
Related papers
- Computer synthesizes feed forward/feed back control
- Feed Size Distribution Feedforward Control for a Grinding Mill Circuit
- Identification of the transition from compensatory to feedforward behavior in manual control
- Partial State Feedback Control System Synthesis Method with Preview Feedforward Compensation
- Feedforward control under the presence of uncertainty
- A Model Of Feedforward Control For Biochemical Reactors
- Intersample ripple resulting from discrete-time feedforward control
- Feedforward as a supplement to feedback adjustment in allowing for feedstock changes