Deep Big Multilayer Perceptrons for Digit Recognition
نویسندگان
چکیده
The competitive MNIST handwritten digit recognition benchmark has a long history of broken records since 1998. The most recent advancement by others dates back 8 years (error rate 0.4%). Good old on-line back-propagation for plain multi-layer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark with a single MLP and 0.31% with a committee of seven MLP. All we need to achieve this until 2011 best result are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning.
منابع مشابه
Deep, Big, Simple Neural Nets for Handwritten Digit Recognition
Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning.
متن کاملRecognition of Handwritten Digits Using Multilayer Perceptrons
Neural networks are often used for pattern recognition. They prove to be a popular choice for OCR (Optical Character Recognition) systems, especially when dealing with the recognition of printed text. In this paper, multilayer perceptrons are used for the recognition of handwritten digits. The accuracy achieved proves that this application is a working prototype that can be further extended int...
متن کاملPersian handwritten digits recognition: A divide and conquer approach based on mixture of MLP experts
In pursuit of Persian handwritten digit recognition, many machine learning techniques have been utilized. Mixture of experts (MOE) is one of the most popular and interesting combining methods which has great potential to improve performance in machine learning. In MOE, during a competitive learning process, the gating networks supervise dividing input space between experts and experts obtain sp...
متن کاملSpeech Recognition Using Demi-Syllable Neural Prediction Model
The Neural Prediction Model is the speech recognition model based on pattern prediction by multilayer perceptrons. Its effectiveness was confirmed by the speaker-independent digit recognition experiments. This paper presents an improvement in the model and its application to large vocabulary speech recognition, based on subword units. The improvement involves an introduction of "backward predic...
متن کاملLocal linear perceptrons for classification
A structure composed of local linear perceptrons for approximating global class discriminants is investigated. Such local linear models may be combined in a cooperative or competitive way. In the cooperative model, a weighted sum of the outputs of the local perceptrons is computed where the weight is a function of the distance between the input and the position of the local perceptron. In the c...
متن کامل