Title: Quantum deep neural networks: A survey

Biography:

Amita Kapoor is an Associate Professor in the Department of Electronics, SRCASW, University of Delhi. She has been actively teaching neural networks for the last twenty years. She did her Masters in Electronics in the year 1996, and her Ph.D. in the year 2011. During her PhD she was awarded prestigious DAAD fellowship to pursue a part of her research work in Karlsruhe Institute of Technology, Karlsruhe, Germany. She had been awarded best Presentation Award at International Conference Photonics 2008 for her paper. She is a member of professional bodies like ACM, AAAI, INNS, and IEEE. She is co-author of two books in the field of Deep Learning using TensorFlow. She has more than 40 research publications in the international journals and conferences. Her present research areas include Machine Learning, Artificial Intelligence, Neural Networks, Robotics, Buddhism (Philosophy and Psychology) and Ethics in AI.

Abstract

Today there is not a single field remains where artificial intelligence and machine learning has left its mark, whether it is understanding the data generated from the CERN collider, identifying exoplanets, detecting Alzheimer or predicting financial markets, its presence can be seen everywhere. At the heart of this overwhelming success are deep neural networks, multi-layered neural network models. This success can be attributed to two major technological advancements, one the specialized processing units which could perform matrix operations (multiplication and addition) in parallel (Graphical processing units GPU and Tensor Processing Units TPU). Second, the internet and the multitude of devices connected to the internet and as a result availability of large amount of data. Despite this tremendous success, there are challenges and areas, the problem of reproducibility in AI, the unsolved problem of artificial general intelligence and excessively long training time for recurrent neural networks and reinforcement learning agents. Quantum deep neural networks with the possibility of achieving computational supremacy promises to offer another technological leap. In this talk we will, provide a comprehensive survey of the available quantum computing infrastructure. The main emphasis of the talk will be quantum models implementing deep neural networks. The existing deep learning models need to be redesigned to work on quantum processors. We will demonstrate how to implement a quantum associative memory and perform an image classification task using quantum neural networks. Finally, the talk will summarize the challenges ahead in this exciting merger of two young fields.