Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
Why is this work in the frame?
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
No Canadian affiliation. An affiliation-only frame — the usual design — would never have seen this work. It is one of the works that make the case for inverting the frame.
Abstract
We present an unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions. The resulting feature extractor consists of multiple convolution filters, followed by a feature-pooling layer that computes the max of each filter output within adjacent windows, and a point-wise sigmoid non-linearity. A second level of larger and more invariant features is obtained by training the same algorithm on patches of features from the first level. Training a supervised classifier on these features yields 0.64% error on MNIST, and 54% average recognition rate on Caltech 101 with 30 training samples per category. While the resulting architecture is similar to convolutional networks, the layer-wise unsupervised training procedure alleviates the over-parameterization problems that plague purely supervised learning procedures, and yields good performance with very few labeled training samples.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
The record
- Venue
- Topic
- Advanced Image and Video Retrieval Techniques
- Field
- Computer Science
- Canadian institutions
- —
- Funders
- Canadian Institute for Advanced ResearchNational Science Foundation
- Keywords
- Pattern recognition (psychology)Artificial intelligenceMNIST databaseComputer scienceClassifier (UML)Unsupervised learningInvariant (physics)Convolutional neural networkCognitive neuroscience of visual object recognitionSigmoid functionFeature extractionMathematicsDeep learningArtificial neural network
- Has abstract in OpenAlex
- yes