Handwritten Digit Recognition Using Multi-Layer Feedforward Neural Networks with Periodic and Monotonic Activation Functions
نویسندگان
چکیده
The problem of handwritten digit recognition is tackled by multi-layer feedforward neural networks with different types of neuronal activation functions. Three types of activation functions are adopted in the network, namely, the traditional sigmoid function, the sinusoidal function and a periodic function that can be considered as a combination of the first two functions. To speed up the learning, as well as to reduce the network size, the Extended Kalman Filter (EKF) algorithm conjunct with a pruning method is used to train the network. Simulation results show that periodic activation functions perform better than monotonic ones in solving multi-cluster classification problems such as handwritten digit recognition.
منابع مشابه
Persian Handwritten Digit Recognition Using Particle Swarm Probabilistic Neural Network
Handwritten digit recognition can be categorized as a classification problem. Probabilistic Neural Network (PNN) is one of the most effective and useful classifiers, which works based on Bayesian rule. In this paper, in order to recognize Persian (Farsi) handwritten digit recognition, a combination of intelligent clustering method and PNN has been utilized. Hoda database, which includes 80000 P...
متن کاملRecognition of Handwritten Digits and Human Faces by Convolutional Neural Networks
Convolutional neural networks provide an eecient method to constrain the complexity of feedforward neural networks by weightsharing. This network topology has been applied in particular to image classiication when raw images are to be classi-ed without preprocessing. In this paper two variations of convolutional networks-Neocognitron and Neoperceptron-are compared with classiiers based on fully...
متن کاملA Minimal Spiking Neural Network to Rapidly Train and Classify Handwritten Digits in Binary and 10-Digit Tasks
This paper reports the results of experiments to develop a minimal neural network for pattern classification. The network uses biologically plausible neural and learning mechanisms and is applied to a subset of the MNIST dataset of handwritten digits. The research goal is to assess the classification power of a very simple biologically motivated mechanism. The network architecture is primarily ...
متن کاملNeural networks with periodic and monotonic activation functions: a comparative study in classi cation problems
This article discusses a number of reasons why the use of non-monotonic functions as activation functions can lead to a marked improvement in the performance of a neural network. Using a wide range of benchmarks we show that a multilayer feed-forward network using sine activation functions (and an appropriate choice of initial parameters) learns much faster than one incorporating sigmoid functi...
متن کامل