This talk will cover the basics of building neural networks for software engineers, through neural weights and biases, activation functions, supervised learning, and gradient descent. I'll show you some tips and best practices for effective training, such as learning rate decay, gradient descent regularization, and the subtleties of overfitting. Be aware that dense and convolutional neural networks are key to any modern implementation. This session starts with low-level Tensorflow and also includes a sample of high-level Tensorflow code using layers and data sets.
University of Sherbrooke
Assistant Professor
Dr. Nadia Tahiri received the M.Sc. and Ph.D. degrees in Computer Science from the University of Quebec in Montreal, Canada. She was a Postdoctoral Researcher working on QSAR/PBPK model prediction in environmental health sciences at the University of Montreal, Canada. She has received several awards and scholarships, author of scientific works that have been published in prestigious journals, …
Dr. Nadia Tahiri received the M.Sc. and Ph.D. degrees in Computer Science from the University of Quebec in Montreal, Canada. She was a Postdoctoral Researcher working on QSAR/PBPK model prediction in environmental health sciences at the University of Montreal, Canada. She has received several awards and scholarships, author of scientific works that have been published in prestigious journals, conferences, and book chapters. She is currently an assistant professor in the Department of Computer Science at the University of Sherbrooke. Her research interests include bioinformatics, phylogenetic tree, phylogeography, clustering, classification, computational biology, supertree, and consensus tree. Nadia is also very involved in community initiatives that promote women in technology and make committee programs more inclusive (the right measures for equity, diversity, and inclusion) as a committee scientific, an active member of ACM Canadian Celebration of Women in Computing, an ambassador of Women Techmakers, and an organizer of GDG Montreal (collaboration)/GDG Cloud Sherbrooke (lead).
GDSC Lead
