Scribd
Upload
67 views3 pages

Course Outline: DLCP Curriculum Walkthrough

Uploaded by

promila09
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
67 views3 pages

Course Outline: DLCP Curriculum Walkthrough

Uploaded by

promila09
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Course Outline

DLCP Curriculum Walkthrough

1. Deep Learning Intro


2. Program Overview
3. Pedagogy
4. Course Modules & Projects
5. Learning Journey.

Deep Learning
We are only about a year into the worldwide Deep Learning explosion, and only about 5
years into its widespread use outside of the research laboratory. But in this very short period
of time, a confluence of factors has helped this become the technique of choice for a variety
of AI problems. These factors are - the proliferation of tools (TensorFlow, PyTorch and the
like), easy availability of GPUs, and a systematic increase in labeled data (tagged photos,
voice interfaces and the like). And as every company is looking to understand how it can use
Deep Learning to get an edge, practitioners in this area have become extremely valuable
and sought after. Roles like Deep Learning Engineer and Computer Vision Engineer have
gone mainstream, and the opportunities in this space seem limitless.

Program Overview
In this course, you will first build strong foundations in neural networks and deep learning.
Then you will use the techniques you learned to solve their most common application areas,
namely Computer Vision and Natural language processing. In the process, you will have
worked on a series of projects in Python, TensorFlow and Keras; and will have used
packages such as NLTK, numpy, matplotlib and scikit-learn.

Deep learning is the most sought after skill in the data science and AI community, and it
requires an experienced hand to guide you in your learning journey. In this program, you will
learn from the best in the world - faculty from IIT Bombay, who have worked with the
inventors and pioneers of Deep Learning, and seasoned practitioners who will give you a
flavour of ‘on-the-ground’ realities.

Pedagogy
DLCP is a 3-month structured, online program with hands-on projects and learning support,
all designed to help you become proficient in Deep Learning. You will learn through a
combination of world-class online content, a series of projects, and exposure to industry
practitioners’ accounts of practical considerations. Weekly support sessions guide your
learning journey, and focus on your projects. You will work on a cloud-based accelerated
computing platform with GPUs and all the requisite software tools that you will need to build
and test computationally intensive Deep Learning models.

This is a program for practitioners, and those who want to be practitioners. So, we focus
intensely on your ability to build real applications using Deep Learning. The projects you
work on - involving both vision and NLP - will give you a taste of what it’s like to grapple with
real-world issues that you will face, and get you comfortable dealing with different types of
data - from text to images and beyond. You will leave with a verified portfolio of projects that
will showcase your newly acquired skills to the world. If you are looking for a job in AI after
this program, you will also be able to answer basic interview questions.
Course Modules

1. Neural Networks & Deep Learning


Ø Neural Networks
Ø Building blocks (feedforward, backpropagation, activation functions,
hyperparameters, gradient descent, softmax, cross entropy loss, etc.)
Ø Multi-layer (deep) neural networks
Ø Implementing deep neural networks (learning rate, hyperparameter selection,
weight initialization, etc.)

2. Computer Vision
Ø Convolutional Neural Networks(CNN)
Ø Image processing using CNN
Ø Pre-processing, semantic segmentation, localization and detection
Ø CNN architectures and Transfer Learning

3. Natural Language Processing


Ø Recurrent Neural Networks (RNN) & Long-short term memory (LSTM)
Ø Common NLP techniques (Bag-of-words, POS tagging, tokenization, stop
words, etc.)
Ø Word embedding (word2vec, GloVe)
Ø Sentiment analysis, Machine translation

In the process, you will also build your foundations, and develop proficiency in a series of
important tools.

Foundations

Ø Python for Data Science


Ø Linear Algebra - Vectors, Matrices, Tensors
Ø Optimization techniques like Gradient Descent
Ø Necessary statistics, probability and differential calculus

Projects

As part of this program, you will use these tools to work on three projects spread across:
1. Neural Networks
2. Computer Vision
3. Natural Language Processing
You will work on these projects using our GPU-enabled lab that will help you learn and solve
problems without buying or installing the computing infrastructure yourself.

Here are the kinds of projects you will be working on as part of this program:
Ø Face Recognition Algorithm (Computer Vision): Recognize, identify and classify faces within
images using CNN and image recognition algorithms.
Ø Fake News Detection (Natural Language Processing): Explore how sequential models in
Deep Learning can be used to distinguish between reliable and unreliable news stories.

Note: The actual projects are subject to change based on the availability of datasets.

You might also like