Scribd
Upload
63 views

Deep Learning Workshop

This document summarizes a deep learning workshop that aims to provide a holistic understanding of deep learning and its applications. The workshop will cover basics of neural networks and deep learning, mathematics and programming for deep learning, and practical applications using TensorFlow and Keras. Attendees will learn how to train neural networks, convolutional neural networks, and LSTM networks to solve complex problems in fields like computer vision, natural language processing, and recommendations. The workshop requires a laptop and basic programming knowledge in Python. It is taught by an experienced data analyst and guest faculty at IIM Bangalore.

Uploaded by

Indhu R
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
63 views

Deep Learning Workshop

This document summarizes a deep learning workshop that aims to provide a holistic understanding of deep learning and its applications. The workshop will cover basics of neural networks and deep learning, mathematics and programming for deep learning, and practical applications using TensorFlow and Keras. Attendees will learn how to train neural networks, convolutional neural networks, and LSTM networks to solve complex problems in fields like computer vision, natural language processing, and recommendations. The workshop requires a laptop and basic programming knowledge in Python. It is taught by an experienced data analyst and guest faculty at IIM Bangalore.

Uploaded by

Indhu R
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Deep Learning Workshop

---------------------------------

Deep Learning is a new area of Machine Learning research, which has been introduced with the
objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence.

This course is intended to give a holistic understanding on Deep Learning and its applications. It would
cover:

• Basics of Neural Networks and Deep Learning


• Mathematics and Programming for Deep Learning
• Detailed application oriented approach towards learning Deep Learning
• Tensor Flow and Keras based practicals
SUMMARY

Objective
Machine learning is one of the fastest-growing and most exciting fields out there, and deep learning
represents its true bleeding edge. In this course, you’ll develop a clear understanding of the motivation
for deep learning, and design intelligent systems that learn from complex and/or large-scale datasets.

We’ll show you how to train and optimize basic neural networks, convolutional neural networks, and
long short term memory networks. Complete learning systems in TensorFlow and Keras will be
introduced with working examples.

You will learn to solve new classes of problems that were once thought prohibitively challenging, and
come to better appreciate the complex nature of human intelligence as you solve these same problems
effortlessly using deep learning methods.

Hardware and Software

• A laptop running 64 bit OS (Linux/OSX/Windows)


• Minimum 8 GB RAM
• There are several installers necessary, we would be sharing the installations in advance.

Pre-requisites

• A basic understanding of programming concepts


• Programming knowledge of python is a plus

Outline

Introduction to Deep Learning

• Deep learning in the context of Machine Learning and Artificial Intelligence


• What is a neural network?
• Why Deep Learning?

Dive deep into Deep Learning

• Train a deep network using TensorFlow/Keras


• How to choose between deep neural networks?
• Effectively regularize a simple deep network.
• Train a competitive deep network via model exploration and hyper-parameter tuning.
Convolutional Neural Networks**

• Train a simple convolutional neural net.


• Explore the design space for convolutional nets.
• Transfer Learning
• Overview of different architectures – VGG; AlexNet etc.

Recurrent Neural Networks

• BPTT; Vanishing Gradient Problem


• LSTM; GRU
• Character Prediction using Keras

Auto-encoders

• Single layer auto-encoders; Stacked Auto-encoders


• Dimension Reduction
• Anomaly Detection

Deep Natural Language Processing

• Embedding Concept in the context of Recommendation Engines


• Word Embedding
• Word Vector Representations: Glove
• Word Vector Representations: word2vec
• Text Classification using Word Embedding, CNN and RNN

Model Debugging and deployment

• TensorFlow Debugger
• Tensorboard
• Deploying models on AWS Platform

About Instructor

Naveen Kumar Bhansali an alumnus IIM Bangalore, is a Big Data Analyst with
over 12 years of experience in Data Analytics and Data Engineering in industries
as varied as Telecom, Energy, Automotive, and Finance.
He is a guest faculty at IIM Bangalore and has also presented numerous plenary
sessions and papers at the International Conference on Business Analytics and Intelligence.
Linkedin: https://www.linkedin.com/in/nkbhansali/

You might also like