Artificial Intelligence

Day

Topic

Day 1

Explaining the concept of artificial intelligence (AI), with its terminology, applications, historical trajectory, and ethical considerations.

Introduction to the Python Programming language and its applications

Day 2

Introduce Machine learning, how it differs from traditional programming, and how it works. Unfold the terminology- Supervised learning, Unsupervised Learning, Reinforcement learning, classification, Regression, clustering.

Practice reading diverse datasets in Python to improve your data manipulation skills.

Day 3

Defining data and its machine-learning applications, sourcing data, and data processing with visualization.

Data visualization and plotting with Python tools like Matplotlib, and Seaborn.

Day 4

Feature engineering, feature scaling, Performance evaluation measures.

Using scikit-learn and pandas libraries of Python programing language for feature scaling and encoding implementation.

Day 5

Introduce the concept of machine learning algorithms like SVM and Descion tree

Implementing first machine learning model with real data using scikit-learn packages through Python programing language

Day 6

Introduce Deep learning , Deep learning vs machine learning, How deep learning works?, History and applications of deep learning.

Performance Evaluation (Accuracy, Confusion matrix) using TensorFlow or PyTorch libraries .

Day 7

Introduction to ANN, Biological inspiration about ANN, perceptron, Multilayer perceptron, and deep neural network.

ANN implementation using libraries such as TensorFlow.

Day 8

Unfold the terms like, activation function, optimization, loss functions, learning rate.

ANN implementation using libraries of Python programming language such as Tensorflow, Keras, and scikit-learn.

Day 9

Convolution neural network (CNN), How CNN is different from DNN, unford the terms like, kernel, padding, pooling, stride.

CNN implementation using Tensorflow.

Day 10

Any one Popular CNN architecture, transfer learning and fine tuning.

CNN implementation with the help of Tensorflow & Keras libraries.