Skip to Main content Skip to Navigation

Contributions to handwriting recognition using deep neural networks and quantum computation

Abstract : In this thesis, we provide several contributions from the fields of deep learning and quantum computation to handwriting recognition. We begin by integrating some of the more recent deep learning techniques (such as dropout, batch normalization and different activation functions) into convolutional neural networks and show improved performance on the well-known MNIST dataset. We then propose Tied Spatial Transformer Networks (TSTNs), a variant of Spatial Transformer Networks (STNs) with shared weights, as well as different training variants of the TSTN. We show improved performance on a distorted variant of the MNIST dataset. In another work, we compare the performance of Associative Long Short-Term Memory (ALSTM), a recently introduced recurrent neural network (RNN) architecture, against Long Short-Term Memory (LSTM), on the Arabic handwriting recognition IFN-ENIT dataset. Finally, we propose a neural network architecture, which we name a hybrid classical-quantum neural network, which can integrate and take advantage of quantum computing. While our simulations are performed using classical computation (on a GPU), our results on the Fashion-MNIST dataset suggest that exponential improvements in computational requirements might be achievable, especially for recurrent neural networks trained for sequence classification.
Complete list of metadata
Contributor : ABES STAR :  Contact
Submitted on : Monday, March 8, 2021 - 11:42:08 AM
Last modification on : Wednesday, June 15, 2022 - 8:45:06 PM


Version validated by the jury (STAR)


  • HAL Id : tel-03162066, version 1



Bogdan-Ionut Cîrstea. Contributions to handwriting recognition using deep neural networks and quantum computation. Artificial Intelligence [cs.AI]. Télécom ParisTech, 2018. English. ⟨NNT : 2018ENST0059⟩. ⟨tel-03162066⟩



Record views


Files downloads