AI & Machine Learning
Description
AI, or Artificial Intelligence, is a broad field focused on creating machines that can mimic human intelligence, while ML, or Machine Learning, is a specific subset of AI that enables machines to learn from data without explicit programming.
What You will Learn
During this program, you will learn how to build intelligent systems that can analyze data, recognize patterns, and make predictions. You will gain both theoretical knowledge and practical hands-on experience in developing AI models and deploying them.
After this training, you will be able to:
Course Syllabus
AI & ML
-
- Module 1: Introduction to AI & ML
- What is Artificial Intelligence?
- Difference between AI, ML, DL, and Data Science
- Real-world Applications of AI & ML
- Types of Machine Learning
- Supervised Learning
- Unsupervised Learning
- Reinforcement Learning
- AI History and Ethics in AI
-
- Python Basics for AI
- Numpy, Pandas, Matplotlib, Seaborn
- Data Preprocessing and Cleaning
- Exploratory Data Analysis (EDA)
-
- Linear Algebra
- Probability and Statistics
- Calculus (Basic understanding)
- Optimization Techniques (Gradient Descent)
- Regression:
- Linear Regression
- Polynomial Regression
- Classification:
- Logistic Regression
- K-Nearest Neighbors (KNN)
- Decision Trees
- Random Forest
- Support Vector Machines (SVM)
- Model Evaluation Metrics:
- Accuracy, Precision, Recall, F1 Score, ROC-AUC
- Clustering:
- K-Means
- Hierarchical Clustering
- DBSCAN
- Dimensionality Reduction:
- PCA (Principal Component Analysis)
- t-SNE
- Introduction to Neural Networks
- Activation Functions
- Forward and Backpropagation
- Gradient Descent Variants (SGD, Adam)
- Multi-Layer Perceptron (MLP)
- Using TensorFlow and Keras
- Image Processing Basics
- CNN Architecture (Conv, Pooling, Flatten, Dense)
- Applications: Face Recognition, Medical Imaging
- Text Preprocessing
- Bag of Words, TF-IDF
- Sentiment Analysis
- Named Entity Recognition (NER)
- Word Embeddings (Word2Vec, GloVe)
- Transformers and BERT (Introduction)
- Markov Decision Processes (MDPs)
- Q-Learning
- Deep Q-Networks (DQN)
- Applications: Game AI, Robotics
- Model Deployment (Flask, Streamlit)
- Model Monitoring
- AI on the Cloud (Google Cloud AI, AWS Sagemaker, Azure ML)
- Introduction to MLOps
- (Students choose one or more based on domain interest)
- AI Chatbot for Customer Support
- Fake News Detection using NLP
- Image Classification for Medical Diagnosis
- Sales Prediction Model
- AI-powered Resume Screener
- Recommender System
Hook up Course
- StartsThis Week
- Duration6 Months, 6 hrs / week