University of Kentucky

MA 721: Topics in Numerical Analysis: Deep Learning

Fall 2017

MWF 1:00 pm - 1:50 pm, CB 347

List of Reading for Class Presentations

Please prepare slides for your presentation and submit it by email at least three days before the planned presentation date for comments/grading.

Paper Presenter Week
Introduction to Tensorflow Liu Liu 10/6 slides
Maxout Networks Jiho Noh 10/11 slides
Improving the convergence of back-propagation learning with second order methods Kasey Bray 10/16 slides
ADADELTA: An Adaptive Learning Rate Method Daniel Cotter 10/18 slides
Adam: A Method for Stochastic Optimization Xinxin Zuo 10/20 slides
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift Devin Willmott 10/23 slides
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization Ryan Peters 10/25 slides
Understanding the difficulty of training deep feedforward neural networks Qiyue Wang 10/27 slides
Random Walk Initialization for Training Very Deep Feedforward Networks Wenhua Jiao 10/30 slides
Visualizing and Understanding Convolutional Networks Gongbo Liang 11/1 slides
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification Gayan Maduranga 11/3 slides
All you need is a good init Qi Sun 11/5 slides
Going deeper with convolutions Caylin Hickey 11/8 slides
Network In Network Kshitija Taywade 11/10 slides
Deep Residual Learning for Image Recognition Jinpeng Liu 11/13 slides
Introduction to Theano Amanuel Zeryihun 11/17
Adaptive nonlinear system identification with echo state networks. Drew Duncan 11/20
Long Short-term Memory Derek Jones 11/27 slides
Orthogonal Recurrent Neural Networks with Scaled Cayley Transform Kyle Helfrich 11/29