Dear Gopal Krishna Sharma

You can start with this useful list of contents:

I. Machine Learning

1. Fundamental algorithms:

• Linear regression,

• Logistic regression, and

• Statistical modeling.

2. Advanced algorithms:

• Decision Tree,

• Random Forest,

• Gradient boosting, and

• K-means clustering

3. Model selection, evaluation, and interpretation concepts:

• Regularization,

• Curse of Dimensionality, and

• Cross-validation

4. Supervised and unsupervised learning tools:

• Scikit-learn,

• XGBoost

II. Deep Learning

1. Overview of Neural Networks.

2. Backpropagation techniques

3. Radial Basis functions

4. Principles of Deep Neural Networks.

5. Common Deep Neural Network configurations:

• RNNs,

• CNNs,

• MLPs,

• LSTMs

6. Generative Deep Learning and GANs

7. Engineering Frameworks:

• Keras,

•TensorFlow,

• PyTorch

III. Reinforcement Learning

1. Monte Carlo Method

2. Q-Learning Method

3. Deep Q Network Method

4. Q-Learning with Normalized Advantage Functions

Reference Materials:

1. MATLAB Deep Learning: With Machine Learning, Neural Networks and Artificial Intelligence

2. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems

3. Deep Learning with Python by FRANÇOIS CHOLLET

Regards

Please look the class

Artificial intelligence

On

YouTube

By

MIT

By

Professor Winston

Go on with the courses in parallel with try to write a review paper or you an also say it as survey paper on any one particular sub-field of your interest. If you can do it and it works for you then you go on with remaining sub-fields of AI. AI is not a small thing its like a ocean full of sub-fields.