Back

Speaker "Viswanath Puttagunta" Details Back

 

Topic

Deep Learning with TensorFlow: Understanding Tensors, Computation Graphs, Images, Text

Abstract

- The elements of Neural Networks: Weights, Biases, Activation functions - MNIST (Hand writing recognition) using simple NN in TensorFlow (Introduce Tensors, Computation Graphs) - MNIST using Convolution NN in TensorFlow - Understanding words and sentences as Vectors - word2vec in TensorFlow - Summary.. where to go next (LSTM).. and other DL tools (Caffe, Theano, Torch)

Profile

Viswanath is currently breaking down various Statistics and neural network frameworks including scikit-learn, gensim, Spark Core, MLlib, Hadoop, caffe, TensorFlow to fundamental operations that can be optimized for ARM SoCs. Viswanath's background is in Statistics and Signal Processing, where he has designed and implemented algorithms related to Discriminant Analysis, K Nearest Neighbors, Convolution Neural Networks to name a few.