By the end of this program, participants will have practical knowledge of machine learning algorithms, deep learning techniques, and be able to develop real-world AI applications.
Overview of AI, ML, and their applications. Understanding supervised vs unsupervised learning.
Build a simple ML model using Scikit-learn.
Core Python Libraries for Data Science: NumPy, Pandas, Matplotlib, and Scikit-learn.
Preprocess data and implement basic data analysis using Python.
Linear Regression, Logistic Regression, and evaluating model performance.
Implement a linear regression model to predict house prices.
K-Nearest Neighbors (KNN), Decision Trees, Random Forest, and Support Vector Machines.
Build a classification model to predict user churn.
Introduction to Neural Networks, activation functions, and backpropagation.
Create a simple neural network using TensorFlow.
Understanding CNNs for image classification and object detection.
Build a CNN for digit recognition using the MNIST dataset.
Introduction to RNNs and Long Short-Term Memory (LSTM) for time-series data.
Develop a time-series prediction model using LSTM.
Techniques for evaluating model performance. Hyperparameter optimization.
Use GridSearchCV to optimize a model.
Introduction to text processing and sentiment analysis using NLP.
Build a text classification model using NLP techniques.
Applying AI in real-world domains like healthcare, finance, and retail.
Research and present an AI application in healthcare.
Deploying AI models to production environments and scaling for real-time applications.
Deploy a model using Flask or Django and connect it to a front-end.
Final project using all AI/ML concepts learned. Preparing for AI/ML job interviews.
Develop an AI project for a real-world problem and present it to the class.
