Anthill Inside 2017

On theory and concepts in Machine Learning, Deep Learning and Artificial Intelligence. Formerly Deep Learning Conf.

Deep Learning with TensorFlow

Submitted by Abdul Muneer (@abdul-muneer) on Wednesday, 26 April 2017

videocam_off

Technical level

Intermediate

Section

Workshop

Status

Submitted

Vote on this proposal

Login to vote

Total votes:  +7

Abstract

TensorFlow is an open source software library for numerical computation using data flow graphs. Created by Google Brain, it was quickly adopted by the machine learning community after it was open sourced. Now it is adopted by industry pioneers like DeepMind at Google, OpenAI, IBM etc. and is fast becoming the go-to library for implementing deep neural networks.
This workshop aims to cover the core APIs, graph defenition and execution, tensorboard visualization, and implementation of Deep Learning Models with TensorFlow.
The workshop is intended for developers who know Python, Numpy and are at least remotely familiar with machine learning.

Outline

Introduction to TensorFlow
Building TensorFlow Graph
Tensors - tensorflow data types
TensorFlow operations
Sessions
Variables and Name scopes
Tensorboard visualization
Implement a Convolutional Neural Network (Convolution, non-linearity, pooling, fully connected)

Requirements

The workshop will be conducted using Jupyter Notebooks. Participants should bring a system with Python 3, Numpy and Jupyter Notebook installed.

Speaker bio

I implement deep neural network models using tensorflow at minds-ai. My focus is on segmentation neural networks with applications in smart cars and health care systems.
When I am free from day job, I also conduct corporate trainings on Python.

Links

Comments

Login with Twitter or Google to leave a comment