online training on AI for research/industry
Lesson 1: General Overview of Artificial Intelligence and Machine Learning
1. Introduction to AI and ML
2. History, goals, and real-world applications across domains.
3. Difference between AI, ML, and Data Science.
4. Types of Machine Learning
5. Supervised, Unsupervised, Reinforcement Learning.
6. Practical examples and use cases of AI and ML
Lesson 2 Introduction to Data Science
1. Data collection methods.
2. Data types and sources.
3. Data preparation, data preprocessing, and cleaning.
5. Data Preparation Techniques - Handling missing values, data transformation and feature extraction, encoding, imputation Identifying features and targets from data
6. Data normalization and scaling.
Lesson 3 Feature Engineering
1. Feature selection and importance.
2. Dimensionality reduction.
Lesson 4 Building ML Models
1. Data splitting: training, validation, testing.
2. Training a simple ML model.
3. Overfitting and underfitting.
Lesson 5 Supervised Learning
1. Classification: Logistic Regression, Decision Trees, KNN, Naive Bayes, SVM.
2. Regression: Linear Regression, Ridge, Lasso, decision tree, random forest etc.
3. Applications and model comparison.
Lesson 6 Unsupervised Learning
1. Clustering: K-Means, DBSCAN, Hierarchical.
2. Association Rules and Dimensionality Reduction (PCA).
second section
Lesson 7: Decision Trees and Ensemble Learning
1. Decision Trees in depth.
2. Ensemble methods: Random Forest, Bagging, Boosting: AdaBoost, XGBoost
Lesson 8 Model Evaluation Metrics
1. Classification: Accuracy, Precision, Recall, F1-Score, Confusion Matrix.
2. Regression: MAE, MSE, RMSE, R².
Lesson 9 Reinforcement Learning
1. Key concepts: agents, environment, reward, policy.
2. Q-learning and applications.
Lesson 10 Generative AI
Introduction to generative models.
1. GANs (Generative Adversarial Networks) basics and applications.
Lesson 11 Prompt Engineering
Lesson 12 Deep Learning
1. Introduction to Neural Networks.
2. Activation functions, backpropagation.
3. CNNs, RNNs, LSTMs – structure and applications.
Third section
Lesson 13: Image Recognition
1. Basics of image processing.
2. Using CNNs for image classification tasks.
Lesson 14 Speech Recognition
1. Audio data basics.
2. Using RNNs and Deep Learning for speech-to-text models.
Lesson 15 Natural Language Processing (NLP)
1. Tokenization, stemming, sentiment analysis.
2. NLP applications like chatbots, translators, summarizers.
Lesson 16 Recommended Systems
Lesson 17 Prompt Engineering
Lesson 18 Transformers and LLMs
1. Introduction to transformer architecture.
2. Pretrained models (BERT, GPT).
3. Use of LLMs in real-world AI systems.