Open AccessProceedings Article
Learning to categorize objects using temporal coherence
Suzanna Becker
- 30 Nov 1992
- Vol. 5, pp 361-368
TL;DR: It is demonstrated that the network can learn, entirely unsupervised, to classify an ensemble of several patterns by observing pattern trajectories, even though there are abrupt transitions from one object to another between trajectories.
read more
Abstract: The invariance of an objects' identity as it transformed over time provides a powerful cue for perceptual learning. We present an unsupervised learning procedure which maximizes the mutual information between the representations adopted by a feed-forward network at consecutive time steps. We demonstrate that the network can learn, entirely unsupervised, to classify an ensemble of several patterns by observing pattern trajectories, even though there are abrupt transitions from one object to another between trajectories. The same learning procedure should be widely applicable to a variety of perceptual learning tasks.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Slow feature analysis: unsupervised learning of invariances
TL;DR: Slow feature analysis (SFA) is a new method for learning invariant or slowly varying features from a vectorial input signal that is guaranteed to find the optimal solution within a family of functions directly and can learn to extract a large number of decor-related features, which are ordered by their degree of invariance.
In search of common foundations for cortical computation.
William A. Phillips,Wolf Singer +1 more
TL;DR: Physiological evidence for synchronization, CFs, and plasticity of the RF and CF connections is described and it is shown how CFs can guide both learning and processing without becoming confused with the transmission of RF information.
Blind Source Separation Using Temporal Predictability
TL;DR: It is shown that this property can be used to recover source signals from a set of linear mixtures of those signals by finding an un-mixing matrix that maximizes a measure of temporal predictability for each recovered signal.
Uncovering the structure of clinical EEG signals with self-supervised learning.
TL;DR: The results suggest that self-supervision may pave the way to a wider use of deep learning models on EEG data, and linear classifiers trained on SSL-learned features consistently outperformed purely supervised deep neural networks in low-labeled data regimes while reaching competitive performance when all labels were available.
219
Face image analysis by unsupervised learning and redundancy reduction
Marian Stewart Bartlett,Donald I. Macleod +1 more
- 01 Jan 1998
TL;DR: The final chapter modeled the development of viewpoint invariant responses to faces from visual experience in a biological system by encoding spatio-temporal dependencies.
104
References
•Proceedings Article
Handwritten Digit Recognition with a Back-Propagation Network
Yann LeCun,Bernhard E. Boser,John S. Denker,John S. Denker,D. Henderson,Richard Howard,W. Hubbard,Lawrence D. Jackel +7 more
- 01 Jan 1989
TL;DR: Minimal preprocessing of the data was required, but architecture of the network was highly constrained and specifically designed for the task, and has 1% error rate and about a 9% reject rate on zipcode digits provided by the U.S. Postal Service.
Neocognitron: A Hierarchical Neural Network Capable of Visual Pattern Recognition
TL;DR: The operation of tolerating positional error a little at a time at each stage, rather than all in one step, plays an important role in endowing the network with an ability to recognize even distorted patterns.
1.1K
Learning invariance from transformation sequences
TL;DR: In this paper, a local learning rule is proposed to learn to generalize across such transformations, where the network is exposed to temporal sequences of patterns undergoing the transformation, and the network learns invariance to shift in retinal position.
741
•Proceedings Article
Training Stochastic Model Recognition Algorithms as Networks can Lead to Maximum Mutual Information Estimation of Parameters
John S. Bridle
- 01 Jan 1989
TL;DR: It is shown that once the output layer of a multilayer perceptron is modified to provide mathematically correct probability distributions, and the usual squared error criterion is replaced with a probability-based score, the result is equivalent to Maximum Mutual Information training.
•Proceedings Article
Shape recognition and illusory conjunctions
Geoffrey E. Hinton,Kevin J. Lang +1 more
- 18 Aug 1985
TL;DR: One way to achieve viewpoint-invariant shape recognition is to impose a canonical, object-based frame of reference on a shape and to describe the positions, sizes and orientations of the shape's features relative to the imposed frame.