Handwritten Digit Recognition via Unsupervised Learning
نویسندگان
چکیده
We present the results of several unsupervised algorithms tested on the MNIST database as well as techniques we used to improve the classification accuracy. We find that spiking neural network outperforms kmeans clustering and reaches the same level as the supervised SVM. We then discuss several inherent issues of unsupervised methods for the handwritten digit classfication problem and propose several methods to further improve the accuracy.
منابع مشابه
Detection of ambiguous patterns in a SOM based recognition system: application to handwritten numeral classification
This work presents a system for pattern recognition that combines a self-organising unsupervised technique (via a Kohonen-type SOM) with a bayesian strategy in order to classify input patterns from a given probability distribution and, at the same time, detect ambiguous cases and explain answers. We apply the system to the recognition of handwritten digits. This proposal is intended as an impro...
متن کاملPersian 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 کاملSnap-drift ADaptive FUnction Neural Network (SADFUNN) for Optical and Pen-Based Handwritten Digit Recognition
An ADaptive Function Neural Network (ADFUNN) is combined with the on-line snap-drift learning method in this paper to solve an Optical Recognition of Handwritten Digits problem and a Pen-Based Recognition of Handwritten Digits problem. SnapDrift [1] employs the complementary concepts of minimalist learning (snap) and drift (towards the input patterns) learning, and is a fast unsupervised method...
متن کاملTraining Neocognitron to Recognize Handwritten Digits in the Real World
Using a large scale real-world database ETL-I, we show that the neocognitron trained by unsupervised learning with a winner-take-all process can recognize handwritten digits with a recognition rate higher than 9'7%. W e use the technique of dual thresholds fo r feature-extracting S-cells, and higher threshold values are used in the learning than in the recognition phase. W e discuss how the thr...
متن کاملArabic Handwritten Digit Recognition Based on Restricted Boltzmann Machine and Convolutional Neural Networks
Handwritten digit recognition is an open problem in computer vision and pattern recognition, and solving this problem has elicited increasing interest. The main challenge of this problem is the design of an efficient method that can recognize the handwritten digits that are submitted by the user via digital devices. Numerous studies have been proposed in the past and in recent years to improve ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2015