Artificial Intelligence &

Deep Learning

Duration Prerequisite
Computer Skills, Basic Maths &
80 Hours Basic Data Science Concepts
Course objectives
The certification course has a teaching duration of 80 hours and has been designed for
professionals with an aptitude for statistics and a background in programming language such
Python, R, etc. Artificial Intelligence (AI) and Deep Learning training helps students in Building
Applications, understanding Neural Network Architectures, Structuring Algorithms for new Al
Machines and minimizing errors through Advanced Optimization Techniques.

Learning Outcomes Who should attend

 Be able to build AI system using Deep
 Candidates aspiring to become Data
Learning algorithms.
Scientists or Deep Learning & AI
 Be able to deal with unstructured data such experts.
as videos, images, audio, text, etc.
 Analytics Managers / Professionals,
 Be able to implement Deep Learning Business Analyst, Developer.
solutions and Image Processing applications
 Graduates who are looking to build a
using Convolution Neural Networks.
career in Machine Learning, Deep
 Be introduced to analyse sequence data and Learning and AI.
perform Text Analytics and Natural
 Employees of organizations, who are
Language Processing (NLP) using Recurrent
planning to focus on building Al
Neural Networks.
applications.
 Be able to effectively use various Python
 Finally - Students who are aiming to
libraries such as Keras, TensorFlow, OpenCV,
work in the IT Industry on emerging
PyTorch, etc., which are used in solving AI
technologies.
and Deep Learning problem.

 Learn about the applications of Graphical

Processing Units (GPUs) in using Deep
Learning algorithms.
 Course Outline

1 Module 1

Introduction to Artificial Intelligence and Deep Learning

• All About 360DigiTMG & Innodatatics Inc., USA
• Dos and Don'ts as a Participant
• Introduction to Artificial intelligence and Deep learning
• Course Outline, Road Map, and Takeaways from the course
• Cross-Industry Standard Process for Data Mining
• Artificial Intelligence Applications

2 Module 2

Introduction to Python Libraries

• Introduction to Deep Learning libraries – Torch, Theono, Caffe,
TensorFlow, Keras, OpenCV and PyTorch
• Deep Dive into TensorFlow, Keras, OpenCV and PyTorch
• Introduction to Anaconda, R, RStudio, Jupyter and Spyder
• Environment Setup and Installation Methods of Multiple Packages

3 Module 3

Machine Learning Primer

• Introduction to Machine Learning
• Machine Learning and its types - Supervised Learning,
Unsupervised Learning, Reinforcement Learning,
Semi-Supervised Learning, Active Learning, Transfer
Learning, Structured Prediction
• Understanding Business Problem – Business Objectives
& Business Constraints
• Data Collection - Surveys and Design of Experiments
• Data Types namely Continuous, Discrete, Categorical,
Count, Qualitative, Quantitative and its identification and
application
 • Further classification of data in terms of Nominal, Ordinal, Interval & Ratio types
• Balanced versus Imbalanced Datasets
• Cross Sectional versus Time Series vs Panel / Longitudinal Data
• Batch Processing vs Real Time Processing
• Structured vs Unstructured vs Semi-Structured Data
• Big vs Not-Big Data
• Data Cleaning / Preparation - Outlier Analysis, Missing Values Imputation
Techniques, Transformations, Normalization / Standardization, Discretization
• Sampling Techniques for Handling Balanced vs. Imbalanced Datasets
• Measures of Central Tendency & Dispersion
1) Mean/Average, Median, Mode
2) Variance, Standard Deviation, Range
• Various Graphical Techniques to Understand Data
1) Bar Plot
2) Histogram
3) Boxplot
4) Scatter Plot
• Feature Engineering – Feature Extraction & Feature Selection
• Error Functions - Y is Continuous - Mean Error, Mean Absolute Deviation, Mean
Squared Error, Mean Percentage Error, Root Mean Squared Error, Mean Absolute
Percentage Error
• Error Functions - Y is Discrete - Cross Table, Confusion Matrix, Binary Cross
Entropy & Categorical Cross Entropy
• Machine Learning Projects Strategy

4  Module 4

Mathematical Foundations
• Optimizations – Applications
• Foundations – Slope, Derivatives & Tangent
• Derivatives in Optimization
• Maxima & Minima- First Derivative and Second Derivative Test, Partial Derivatives,
Cross Partial Derivatives, Saddle Point, Determinants, Minor and Cofactor
• Linear Regression Ordinary Least Squares using Calculus
5 Module 5

Deep Learning Primer

• Human Brain – Introduction to Biological & Artificial Neuron
• Compositionality in Data – Images, Speech & Text
• Mathematical Notations
• Introduction to ANN
• Neuron, Weights, Activation Function, Integration Function, Bias and Output

6 Module 6

Perceptron Algorithm and Back Propagation Neural Network Algorithm

• Introduction to Perceptron
• Introduction to Multilayer Perceptron (MLP)
• Activation Functions – Identity Function, Step Function, Ramp Function,
Sigmoid Function, Tanh Function, ReLU, ELU, Leaky ReLU & Maxout
• Back Propagation Visual Demonstration
• Network Topology – Key Characteristics and Number of Layers
• Weights Calculation in Back Propagation

7  Module 7

Artificial Neural Network (ANN), Multilayer Perceptron (MLP)

• Error Surface – Learning Rate & Random Weight Initialization
• Local Minima issues in Gradient Descent Learning
• Is DL a Holy Grail? Pros and Cons
• Practical Implementation of MLP/ANN in Python using Real Life Use Cases
• Segregation of Dataset - Train, Test & Validation
• Data Representation in Graphs using Matplotlib
• Deep Learning Challenges – Gradient Primer, Activation Function, Error Function,
Vanishing Gradient, Error Surface challenge, Learning Rate Challenges, Decay Parameter,
Gradient Decent Algorithmic Approaches, Momentum, Nestrov Momentum, Adam,
AdaGrad, Adadelta & RMSProp
• Deep Learning Practical Issues – Avoid Overfitting, DropOut, DropConnect, Noise, Data
Augmentation, Parameter Choices, Weights Initialization (Xavier, etc.)
8 Module 8

Convolution Neural Networks - CNN

• ImageNet Challenge – Wining Architectures, Difficult Vision Problems &
Hierarchical Approach
• Parameter Explosion with MLP
• Convolution Networks - 1D ConvNet, 2D ConvNet, Transposed Convolution
• Convolution Layers with Filters and Visualizing Convolution Layers
• Pooling Layer, Padding, Stride
• Transfer Learning - VGG16, VGG19, Resnet, GoogleNet, LeNet, etc.
• Practical Issues – Weight Decay, DropOut, Data Manipulation Techniques &
Batch Normalization

9  Module 9

Image Processing and Computer Vision

• Introduction to Vision
• Importance of Image Processing
• Image Processing Challenges – Interclass Variation, View Point Variation,
IIlumination, Background Clutter, Occlusion & Number of Large Categories
• Introduction to Image – Image Transformation, Image Processing Operations &
Simple Point Operations
• Noise Reduction – Moving Average & 2D Moving Average
• Image Filtering – Linear & Gaussian Filtering
• Disadvantage of Correlation Filter
• Introduction to Convolution
• Boundary Effects – Zero, Wrap, Clamp & Mirror
• Image Sharpening
• Template Matching
• Edge Detection – Image Filtering, Origin of Edges, Edges in Images as Functions,
Sobel Edge Detector
• Effect of Noise
• Laplacian Filter
• Smoothing with Gaussian
• LOG filter – Blob Detection
 • Noise Reduction using Salt & Pepper Noise using Gaussian Filter
• Nonlinear Filters
• Bilateral Filters
• Canny Edge Detector - Non Maximum Suppression, Hysteresis Thresholding
• Image Sampling & Interpolation – Image Sub Sampling, Image Aliasing , Nyquist
Limit, Wagon Wheel Effect, Down Sampling with Gaussian Filter, Image Pyramid,
Image Up-sampling
• Image Interpolation – Nearest Neighbour Interpolation, Linear Interpolation,
Bilinear Interpolation & Cubic Interpolation

10  Module 10

Recurrent Neural Network - RNN

• Introduction to Adversaries
• Language Models – Next Word Prediction, Spell Checkers, Mobile Auto Correct,
Speech Recognition & Machine Translation
• Traditional Language Model
• Disadvantages of MLP
• Introduction to State & RNN cell
• Introduction to RNN
• RNN Language Models
• Back Propagation Through Time
• RNN Loss Computation
• Types of RNN – One to One, One to Many,
Many to One, Many to Many
• Introduction to the CNN and RNN
• Combining CNN and RNN for Image Captioning
• Architecture of CNN and RNN for Image Captioning
• Bidirectional RNN
• Deep Bidirectional RNN
• Disadvantages of RNN
11 Module 11
CNN + RNN Variants, Fast R-CNN and Mask R-CNN
• CNN-RNN Variants
• R-CNN
• Fast R-CNN
• Faster R-CNN
• Mask R-CNN

12  Module 12

Long Short Term Memory - LSTM

• Introduction to LSTM – Architecture
• Importance of Cell State, Input Gate, Output Gate, Forget Gate,
Sigmoid and Tanh
• Mathematical Calculations to Process Data in LSTM
• RNN vs LSTM - Bidirectional vs Deep Bidirectional RNN
• Deep RNN vs Deep LSTM

13 Module 13

Gates Recurrent Units - GRUs

• Introduction to GRU
• Architecture & Gates - Update Gate, Reset Gate, Current Memory
Content, Final Memory at Current Timestep
• Applications of GRUs

14  Module 14

Autoencoders, Variational Autoencoders, RBM

• Autoencoders
1) Intuition
2) Comparison with other Encoders (MP3 and JPEG)
3) Implementation in Keras
 • Deep Autoencoders
1) Intuition
2) Implementing DAE in Keras
• Convolutional Autoencoders
1) Intuition
2) Implementation in Keras
• Variational Autoencoders
1) Intuition
2) Implementation in Keras
• Introduction to Restricted Boltzmann Machines - Energy Function,
Schematic implementation, Implementation in Tensorflow

15 Module 15

Deep Belief Networks (DBNs)

• Introduction to DBN
• Architecture of DBN
• Applications of DBN
• DBN in Real World

16 Module 16

Generative Adversarial Networks - GANs

• Introduction to Generative Adversarial Networks (GANs)
• Data Analysis and Pre-Processing
• Building Model
• Model Inputs and Hyperparameters
• Model Losses
• Implementation of GANs
• Defining the Generator and Discriminator
• Generator Samples from Training
• Model Optimizer
• Discriminator and Generator Losses
• Sampling from the Generator
17 Module 17

Super Resolution GAN

• Introduction to SRGAN
• Network Architecture - Generator, Discriminator
• Loss Function - Discriminator Loss & Generator Loss
• Implementation of SRGAN in Keras

18  Module 18

Reinforcement Learning and Q-learning

• Reinforcement Learning • Experience Replay or the Value of
• Deep Reinforcement Learning Experience
versus Atari Games • Q-Learning and Deep Q-Network as a
• Maximizing Future Rewards Q-Function

• Policy versus Values Learning • Improving and Moving Beyond DQN

• Balancing Exploration With Exploitation • Keras Deep Q-Network

19  Module 19

Speech Recognition
• Speech Recognition Pipeline • Acoustic Model
• Phonemes • Deep Learning Models
• Pre-processing • Decoding

20  Module 20

Building Chatbot & RASA NLU Framework

• Introduction to Chatbot • Generative Chatbot Development

• NLP implementation in Chatbot • Building a Retrieval Based Chatbot
• Integrating and implementing • Deploying Chatbot in Various
Neural Networks Chatbot Platforms
 Methodology

Lectures with a blend Case study driven

Quizzes and
of theoretical & approach to reiterate
group activities
practical exposure the learning

Group discussions to trigger Live project opportunity to engage

cross industry understanding and explore with USA based
of various participants Analytics Consulting firm - Innodatatics

Software Used

Course Deliverables:
 Use case drivers & industry specific curriculum with expert trainers

 Work on (1) Live Project through INNODATATICS, USA

 Additional assignments covering over 100 hours
 Lifetime Learning Management System (LMS) access to recorded
videos, assignments, case studies related to your industry,
algorithms & course materials
 Access to Free webinars and latest industry updates
 Job assistance for getting placed in the field
of Artificial Intelligence and Deep Learning

 24/7 Interaction with our trainer pool through forums

 3 mock interviews to test your readiness to attend the interviews
 Accreditation to international certification bodies

Certificate awarded by

For further details, call us at

1800-212-654321

[email protected] 360digitmg.com

2-56/2/19, 3rd Floor, Vijaya Towers, Ayyappa Society Road, Madhapur, Hyderabad, Telangana 50008

USA | INDIA | MALAYSIA | ROMANIA | SOUTH AFRICA | DUBAI | BAHRAIN