Abstract
The problems are discussed of the recognition of handprinted and spoken digits and the handprinted and spoken English alphabet. Four such experiments were conducted and the results were compared to a conventional nearest-neighbor classifier trained on the same data. Results indicate that neural networks and nearest-neighbor classifiers perform at near the same level of accuracy. For each task, a critical number of neurons can be determined experimentally which yields highest recognition accuracy with least hardware. This number can also measure the classification efficiency of the input feature encoder. Several techniques for optimizing the performance of layered networks are discussed. A constant level added to the input signal biases patterns into the range where the learning rate is highest. Eliminating near-zero weights after learning results in little loss of accuracy. Finally, a novel handwriting encoder is described.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Keywords
Computer scienceHandwritingk-nearest neighbors algorithmAlphabetPattern recognition (psychology)Artificial neural networkArtificial intelligenceEncoderSpeech recognitionClassifier (UML)Feature (linguistics)
Affiliated Institutions
Related Publications
Statistical pattern recognition with neural networks: benchmarking studies
Three basic types of neural-like networks (backpropagation network, Boltzmann machine, and learning vector quantization), were applied to two representative artificial statistic...
Hidden Markov models for character recognition
A hierarchical system for character recognition with hidden Markov model knowledge sources which solve both the context sensitivity problem and the character instantiation probl...
Layered neural nets for pattern recognition
A pattern recognition concept involving first an 'invariance net' and second a 'trainable classifier' is proposed. The invariance net can be trained or designed to produce a set...
Enhancing supervised learning algorithms via self-organization
A neural network processing scheme is proposed which utilizes a self-organizing Kohonen feature map as the front end to a feedforward classifier network. The results of a series...
Reducing transmission error effects using a self-organizing network
The author shows that a Kohonen self-organizing network can be used to reduce the effects of errors in digital transmission of speech, Kohonen learning is used to cause the netw...
Publication Info
- Year
- 1988
- Type
- article
- Volume
- 36
- Issue
- 7
- Pages
- 1162-1168
- Citations
- 263
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
263
OpenAlex
Cite This
Dc Burr
(1988).
Experiments on neural net recognition of spoken and written text.
IEEE Transactions on Acoustics Speech and Signal Processing
, 36
(7)
, 1162-1168.
https://doi.org/10.1109/29.1643
Identifiers
- DOI
- 10.1109/29.1643