Course Details

Artificial Intelligence

Module one – Python Programming

Objectives – At the tip of this Module, you must be in a position to:

• Introduction to Python Programming
• Working with Numbers, Floats and Strings
• Conditional Execution
• Working with Functions and Recursions
• Lists
• List Comprehensions
• More on Strings
• Dictionaries
• File IO
• Regular Expressions
• Classes and Objects
• Debugging tools
• Working with Jumpy

Module a pair of – Machine Learning

Objectives – At the tip of this Module, you must be in a position to:

• Introduction to Machine Learning
• Logistic Regression
• Support Vector Machines
• Decision Trees

Module three – Introduction to Deep Learning

Objectives – At the tip of this Module, you must be in a position to:

• Discuss the revolution of computing.
• Discuss the restrictions of Machine Learning.

List the benefits of Deep Learning over Machine Learning.

• Discuss Real-life use cases of Deep Learning.
• Understand the eventualities wherever Deep Learning is applicable.
• Discuss relevant topics of algebra and Statistics.
• Discuss Machine learning algorithms.
• Discuss model parameters and improvement techniques.

Module four – Fundamentals of Neural Networks.

Objectives – At the tip of this Module, you must be in a position to:

• Define Neural Networks.
• Discuss the coaching Techniques of Neural Networks.
• List totally different Activation and Loss Functions.
• Discuss the various parameters of Neural Networks.
• Gradient Descent.
• Stochastic Gradient Descent.

Module 5: Fundamentals of Deep Networks

Objectives – At the tip of this Module, you must be in a position to:

• Define Deep Learning
• Discuss the discipline Principals of Deep Networks
• List totally different parameters of Deep Networks
• Discuss the Building Blocks of Deep Networks

Module 6: Introduction to Tensor Flow

Objectives – At the tip of this Module, you must be in a position to:

• Define TensorFlow.
• Illustrate however Tensor Flow works.
• Discuss the Functionalities of Tensor Flow.
• Illustrate other ways to put in Tensor Flow.
• Install Tensor Flow.
• Write and Run programs on Tensor Flow.

Module 7: Convolution Neural Networks (CNN)

Objectives – At the tip of this Module, you must be in a position to:

• Define CNNs.
• Discuss the Applications of CNN.

make a case for the design of a CNN.

• List Convolution and Pooling Layers in CNN.
• Understanding and Visualizing a CNN.
• Discuss Fine-tuning and Transfer Learning of CNNs.

Module eight – perennial Neural Networks (RNN)

Objectives – At the tip of this Module, you must be in a position to:

• Define RNN.
• Discuss the Applications of RNN.
• Illustrate however RNN is trained.
• Discuss Long short-run memory(LSTM).

Module 9 – computing

Objectives – At the tip of this Module, you must be in a position to:

• Introduction to computing
• AI eventualities
• Depth 1st Search
• Breadth 1st Search
• Dynamic Programming
• A*Search

Module ten – Project Work

Objectives – At the tip of this Module, you must be in a position to:

• Real Time use cases
• Project Work