Scribd
Upload
41 views

Deep Learning

Uploaded by

dhruva bade
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
41 views

Deep Learning

Uploaded by

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

DEEP LEARNING USING TENSORFLOW AND KERAS

OBJECTIVE

Machine learning is one of the fastest-growing and most exciting fields out there, and deep
learning represents its true bleeding edge. This course is intended to give a holistic
understanding on Deep Learning and its applications. It would cover:
• Neural Networks – Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN)
and Auto Encoders, Recurrent Neural Network (RNN)
• Detailed application-oriented approach towards learning Deep Learning with datasets
on Computer Vision and Natural Language Processing.
• Tensor Flow and Keras based notebooks

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.
DEEP LEARNING USING TENSORFLOW AND KERAS

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)


• We shall be using Google Colab service and hence we would not require any installation.
• Decent Internet Connection

PRE-REQUISITES

• Programming knowledge of python and machine learning is a plus

INSTRUCTOR PROFILE

Naveen Kumar Bhansali has around 15 years of experience as data scientist, advisory
architect and consultant in big data, artificial intelligence, deep learning/machine learning
and business analytics across various domains/verticals such as telecom, retail, aerospace,
e-commerce, education, federal agencies and IT – Exchange & Storage. He has worked
across the globe for clients such as Embraer Brazil, FWD Hong Kong, Bank of Thailand, TIM
Brazil, Hawaiian Telecom USA, Bank of Ayudhya in Thailand, ASOS UK, VTC Hong Kong, etc.
He is an alumnus of Indian Institute of Management (IIM), Bangalore and is also a guest
lecturer on Artificial Intelligence, Deep Learning and Big Data at IIM Bangalore and Amity
University.

He has published an Analytics Cases in Harvard Business Publishing:


• Customer Analytics at Flipkart.com
https://cb.hbsp.harvard.edu/cbmp/product/IMB555-PDF-ENG

• Breaking Barriers – Micro-mortgage Analytics:


http://cb.hbsp.harvard.edu/cb/web/product_detail.seam?E=4848558&R=IMB445-PDF-
ENG&conversationId=8501

Connect with him on Linked in https://www.linkedin.com/in/nkbhansali/

COURSE OUTLINE

Module 1: Introduction to Deep Learning


Representation Learning
Difference between ML/DL/AI
Use case mapping to technique
DEEP LEARNING USING TENSORFLOW AND KERAS

Module 2: Artificial Neural Network (Multi-Layer Perceptron)


Gradient Descent - Mini-batch and Stochastic
Back-propagation; cost function and optimizers
Developing deep learning using Keras
Neural Networks and hyper-parameters
Model Evaluation – Grid Search Cross Validation
Early Stopping

Module 3: Convolutional Neural Networks (CNN) and Recurrent Neural


Networks (RNN)
Overview of Convolutional Neural Network and its applications (Image Analytics)
Transfer Learning
Overview of Recurrent Neural Network
RNN Architectures – LSTM/GRU

Module 5: NLP
Understanding the concept of Embeddings
Word Embedding (Word2Vec, GloVe) & Transfer learning
Embedding Projector and visualizing the embeddings
Applying Embedding layer and building a model in Keras (Sentiment Analysis)

You might also like