Live Coding to predict handwritten digits using TensorFlow

Live Coding to predict handwritten digits using TensorFlow

Details

Neural networks are used as a method of deep learning, one of the many subfields of artificial intelligence. They were first proposed around 70 years ago as an attempt at simulating the way the human brain works, though in a much more simplified form. Individual ‘neurons’ are connected in layers, with weights assigned to determine how the neuron responds when signals are propagated through the network. Previously, neural networks were limited in the number of neurons they were able to simulate, and therefore the complexity of learning they could achieve. But in recent years, due to advancements in hardware development, we have been able to build very deep networks, and train them on enormous datasets to achieve breakthroughs in machine intelligence.

In this live coding session, you will implement a small subsection of object recognition—digit recognition. Using TensorFlow, an open-source Python library developed by the Google Brain labs for deep learning research, you will take hand-drawn images of the numbers 0-9 and build and train a neural network to recognize and predict the correct label for the digit displayed.

While you won’t need prior experience in practical deep learning or TensorFlow to follow along with this tutorial, we’ll assume some familiarity with machine learning terms and concepts such as training and testing, features and labels, optimization, and evaluation.

ORGANIZERS MESSAGE

Get a chance to hear from the experts sharing their knowledge, doing Hands on practice with Industry experts and the work they are doing in this field.

Equonix Tech Lab believes that the outcome of any conference is based on its learning and experience for the delegates. There is already vast content accessible in the open world and we believe there is a need for the event where the participants can get more information on AI from there leaders.

HOW TO RESERVE YOUR SEAT

We need confirmation from all of you immediately. There is a fee
for attending this event.

The session early bird will be : 499/-

** Maximum No of seats allowed 8. Completely First Come, First Serve Basis.**

You can send payment for confirmation via online:

  1. Use this link for transfer.

  2. You can send via paytm. The number is 9560633668.

NOTE

RSVP here is not final confirmation for the events seat. After payment you have to confirm at tanmoydeb@equonix.com.

REQUIRED TOOLS

  1. Windows 7 or later. Only 64 bit.

  2. Ubuntu 16.4 or above (if you don’t have windows)

  3. The system must be 64-bit, x86 desktops or laptops.

  4. Python 3.6 (otherwise the projects will not work)

  5. PyDev on Eclipse.

ABOUT THE SPEAKER

Tanmoy Deb is founder and CEO of Equonix Tech Lab. He has been working into AI/ML based applications, electronics product designing and development for last 12 years. His area of interests are Deep learning based enabled Image Processing (OCR) for Languages on low cost processors, Activity/Object recognition in Surveillance cameras, medical imaging, Sports cameras, robotics using Neural Networks. Also Application development using Tensor Flow in Virtual reality and Augmented Reality in the area of education, healthcare, defense.

TOPICS OF THE SESSION

#Introduction and importance of Machine Learning
#Current Market Trends
#Introduction to MNIST Dataset
#Visualization of Dataset
#Understand the dataset
#Tensorflow Introduction
#Write your first code TensorFlow
#Feature Selection
#Feature Extraction
#Estimation and Classification
#How to improve the results, understand the parameters.

Date : 6th January, 2019
Time : 11AM to 2PM.

VENUE DETAILS

1 Minute walkin distance from Munirka Metro Station (Magenta Line), New Delhi. Please contact 91-9711045221 (Purushottam Mishra) for Direction.

Close Menu