Unsupervised Adaptation of Neural Networks for Chinese Handwriting Recognition

2016 ◽  
Author(s):  
Hong-Ming Yang ◽  
Xu-Yao Zhang ◽  
Fei Yin ◽  
Zhenbo Luo ◽  
Cheng-Lin Liu
Keyword(s):  
Neural Networks ◽  
Handwriting Recognition

Offline continuous handwriting recognition using sequence to sequence neural networks

2018 ◽  
Vol 289 ◽  
pp. 119-128 ◽  
Author(s):  
Jorge Sueiras ◽  
Victoria Ruiz ◽  
Angel Sanchez ◽  
Jose F. Velez
Keyword(s):  
Neural Networks ◽  
Handwriting Recognition

Literature Survey for Applications of Artificial Neural Networks

2022 ◽  
pp. 669-682
Author(s):  
Pooja Deepakbhai Pancholi ◽  
Sonal Jayantilal Patel
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Weather Forecasting ◽  
Handwriting Recognition ◽  
Complete Solution ◽  
Learning System ◽  
E Learning ◽  
Artificial Neural

The artificial neural network could probably be the complete solution in recent decades, widely used in many applications. This chapter is devoted to the major applications of artificial neural networks and the importance of the e-learning application. It is necessary to adapt to the new intelligent e-learning system to personalize each learner. The result focused on the importance of using neural networks in possible applications and its influence on the learner's progress with the personalization system. The number of ANN applications has considerably increased in recent years, fueled by theoretical and applied successes in various disciplines. This chapter presents an investigation into the explosive developments of many artificial neural network related applications. The ANN is gaining importance in various applications such as pattern recognition, weather forecasting, handwriting recognition, facial recognition, autopilot, etc. Artificial neural network belongs to the family of artificial intelligence with fuzzy logic, expert systems, vector support machines.

scholarly journals Hybridizing Evolutionary Computation and Deep Neural Networks: An Approach to Handwriting Recognition Using Committees and Transfer Learning

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-16 ◽  
Author(s):  
Alejandro Baldominos ◽  
Yago Saez ◽  
Pedro Isasi
Keyword(s):  
Neural Networks ◽  
Evolutionary Computation ◽  
Transfer Learning ◽  
Convolutional Neural Networks ◽  
Character Recognition ◽  
Deep Neural Networks ◽  
Handwriting Recognition ◽  
Computational Time ◽  
Learning Models ◽  
Expensive Process

Neuroevolution is the field of study that uses evolutionary computation in order to optimize certain aspect of the design of neural networks, most often its topology and hyperparameters. The field was introduced in the late-1980s, but only in the latest years the field has become mature enough to enable the optimization of deep learning models, such as convolutional neural networks. In this paper, we rely on previous work to apply neuroevolution in order to optimize the topology of deep neural networks that can be used to solve the problem of handwritten character recognition. Moreover, we take advantage of the fact that evolutionary algorithms optimize a population of candidate solutions, by combining a set of the best evolved models resulting in a committee of convolutional neural networks. This process is enhanced by using specific mechanisms to preserve the diversity of the population. Additionally, in this paper, we address one of the disadvantages of neuroevolution: the process is very expensive in terms of computational time. To lessen this issue, we explore the performance of topology transfer learning: whether the best topology obtained using neuroevolution for a certain domain can be successfully applied to a different domain. By doing so, the expensive process of neuroevolution can be reused to tackle different problems, turning it into a more appealing approach for optimizing the design of neural networks topologies. After evaluating our proposal, results show that both the use of neuroevolved committees and the application of topology transfer learning are successful: committees of convolutional neural networks are able to improve classification results when compared to single models, and topologies learned for one problem can be reused for a different problem and data with a good performance. Additionally, both approaches can be combined by building committees of transferred topologies, and this combination attains results that combine the best of both approaches.

Sign in / Sign up

Export Citation Format

Share Document