Introduction to Neural Networks
When: Monday, February 10, 2020
Where: PGH 232
Time: 11:00 AM
Speaker: Dr. Arko Barman, The University of Texas Health Science Center at Houston (UTHealth)
Host: Dr. Gopal PanduranganThe artificial neural network, or simply neural network, is a machine learning technique that evolved from simple models of the neuron in a human brain. Developed over several decades, the theory of neural networks forms the bedrock for the proliferation of deep learning algorithms, models, and tools that have outperformed humans in several tasks in recent years. In this talk, we will focus on how biological neural networks inspired the development of artificial neural networks, the basic underlying model of an artificial neuron, and how non-linearities are incorporated for building diverse, better-performing and more robust models. Further, we will briefly explore how to construct a simple neural network with multiple layers of neurons and how neural networks can be trained using the backpropagation algorithm to “learn” to perform different tasks.
Dr. Arko Barman is a postdoctoral research fellow at The University of Texas Health Science Center at Houston (UTHealth), where his current research focuses on developing imaging-based computer-aided diagnosis systems for stroke, Alzheimer's and other diseases. He received his B.E. degree in Electrical Engineering from Jadavpur University in 2009 and his M.E. degree in Signal Processing from Indian Institute of Science in 2011. He received his Ph.D. in Computer Science at the University of Houston in 2018. Dr. Barman has worked at Broadcom Corporation and PARC (a Xerox company), and has also served as an Assistant Professor at a 4-year engineering college in India. His research interests include Medical Image Computing, Deep Learning, Computer Vision, Machine Learning, Data Mining, and Heuristic Optimization Algorithms. He has also been involved in curriculum design and has taught a diverse range of courses at different levels.