Join Amit Kulkarni, an industry expert and certified AI specialist, as he walks you through the Mastering GenAI course at Sunbeam Pune. This program is designed to help you understand, build, and innovate with AI-powered solutions.

Mastering AI Basics

• Overview of Statistics
  • Definition and importance of statistics
  • Types of statistics: descriptive and inferential
  • Role of statistics in data science and machine learning
  • Basic statistical terminology (population, sample, parameter, statistic)
• Sampling
  • Sampling methods
  • sampling distributions
  • Central Limit Theorem
• Descriptive Statistics
  • Measures of central tendency (mean, median, mode)
  • measures of variability (range, variance, standard deviation)
  • skewness and kurtosis
• Probability:
  • Basic concepts of probability, conditional probability
  • Bayes' theorem.
  • Random variables and probability distributions
• Distributions:
  • Normal distribution
  • Binomial distribution
  • Poisson distribution
  • Uniform distribution
• Hypothesis Testing:
  • Null and alternative hypotheses
  • Type I and Type II errors
  • P-values
  • Confidence intervals
• Correlation Analysis:
  • Pearson correlation
  • Spearman's rank correlation
• Time Series Analysis:
  • Trend analysis
  • Seasonality
  • Moving averages
  • ARMA models
  • ARIMA models
• Data Visualization:
  • Importance of data visualization
  • Principles of effective data visualization
  • Common visualization techniques:
    •   Histograms
    •   Box plots
    •   Scatter plots
    •   Heatmaps
    •   Bar charts
• Data Preprocessing
  • Data cleaning and handling missing values
  • Data transformation (normalization, standardization)
  • Feature engineering and selection
  • Encoding categorical variables
  • Handling imbalanced datasets
  • Data splitting (training, validation, test sets)
  • Data augmentation techniques
  • Outlier detection and handling
• Introduction to Machine Learning
  • Overview of machine learning
  • Types of machine learning:
    • supervised learning
    • unsupervised learning
    • reinforcement learning
    • semi-supervised learning
  • Applications of machine learning
  • Challenges and limitations of machine learning
• Regression Analysis
  • Overview of regression analysis
  • Algorithms for regression:
    •  Linear regression
    •  Ridge regression
    •  Lasso regression
  • Assumptions of regression analysis
  • Model evaluation metrics (R-squared, adjusted R-squared, RMSE, MAE)
  • Model interpretation and communication of results
  • Applications of regression analysis
• Classification
  • Overview of classification
  • Types of classification
  • Evaluation metrics for classification (Confusion matrix, accuracy, precision, recall, F1-score, ROC-AUC)
  • Algorithms for classification:
    • Decision trees
    • k-nearest neighbors (k-NN)
    • Naive Bayes
  • Ensemble methods (Bagging, Boosting, Stacking)
  • Hyperparameter tuning and model selection
  • Cross-validation techniques
  • Applications of classification
• Clustering
  • Overview of clustering
  • Types of clustering:
    • K-means clustering
    • Hierarchical clustering
  • Evaluation metrics for clustering (Silhouette score)
• Dimensionality Reduction
  • Overview of dimensionality reduction
  • Importance of dimensionality reduction
  • Techniques for dimensionality reduction:
    •  Principal Component Analysis (PCA)

Mastering-AI-Advance

• Introduction to Deep Learning
  • Overview of deep learning
  • Differences between traditional machine learning and deep learning
  • Applications of deep learning in various domains
  • Challenges and limitations of deep learning
  • Overview of generative AI
  • Applications of generative AI in various domains
  • Challenges and limitations of generative AI
• Deep Learning Frameworks
  • Overview of popular deep learning frameworks (TensorFlow, PyTorch, Keras)
  • Overview of generative AI frameworks (Huggingface, Langchain)
  • Setting up the environment
• Artificial Neural Networks (ANNs)
  • Feedforward neural networks
  • what is a perceptron
  • Multi-layer perceptrons (MLPs)
  • Activation functions (ReLU, sigmoid, tanh)
  • Loss functions (mean squared error, cross-entropy)
  • Regression and classification using ANNs
  • Model evaluation metrics (accuracy, precision, recall, F1-score)
  • Model interpretability
  • Applications of ANNs in real-world scenarios
  • Hands-on: Build and train ANN model for regression and classification tasks
• Convolutional Neural Networks (CNNs)
  • Overview of CNNs and their architecture
  • Convolutional layers and filters
  • Pooling layers (max pooling, average pooling)
  • Flattening and fully connected layers
  • Applications of CNNs in image processing and computer vision
  • Hands-on: Build and train a CNN for image classification
• Recurrent Neural Networks (RNNs)
  • Overview of RNNs and their architecture
  • ANN vs CNN vs RNN
  • Long Short-Term Memory (LSTM) networks
  • Gated Recurrent Units (GRUs)
  • Applications of RNNs in natural language processing and time series analysis
  • Hands-on: Build and train an RNN for text classification or time series prediction
• Generative Adversarial Networks (GANs)
  • Overview of GANs and their architecture
  • Generator and discriminator networks
  • Training GANs and challenges
  • Applications of GANs in image generation and data augmentation
  • Variants of GANs (DCGAN, CycleGAN, StyleGAN)
  • Hands-on: Build and train a GAN for image generation
• Transfer Learning
  • Overview of transfer learning
  • Fine-tuning pre-trained models
  • Applications of transfer learning in various domains
  • Hands-on: Fine-tune a pre-trained model for a specific task
• Natural Language Processing (NLP)
  • Overview of NLP and its applications
  • Text preprocessing techniques (tokenization, stemming, lemmatization)
  • Word embeddings (Word2Vec, GloVe, FastText)
  • Sequence-to-sequence models
  • Attention mechanisms in NLP
  • Named Entity Recognition (NER)
  • Sentiment analysis
  • Fine-tuning pre-trained models for NLP tasks
  • Hands-on: Build and train an NLP model for text classification or sentiment analysis
• Large Language Models (LLMs)
  • Overview of LLMs and their architecture
  • Transformer architecture
  • Attention mechanisms
  • Pre-training and fine-tuning LLMs
  • Applications of LLMs in natural language processing
  • Hands-on: Fine-tune a pre-trained LLM for text generation or classification
• Retrieval-Augmented Generation (RAG)
  • Overview of RAG
  • How RAG works
  • Applications of RAG in natural language processing
  • Challenges and limitations of RAG
  • Future directions of RAG
  • Hands-on: Build a RAG model for a specific task (e.g., chat with PDF, chat with CSV, chat with text)
  • Evaluation metrics for RAG models
  • Hands-on: Evaluate the performance of a RAG model
• Agentic RAG
  • Overview of agentic RAG
  • How agentic RAG works
  • Applications of agentic RAG in natural language processing
  • Challenges and limitations of agentic RAG
  • Future directions of agentic RAG
  • Hands-on: Build an agentic RAG model for a specific task
• Fine tuning LLMs
  • Overview of fine-tuning LLMs
  • How to fine-tune LLMs
  • Applications of fine-tuning LLMs in natural language processing
  • Challenges and limitations of fine-tuning LLMs
  • Future directions of fine-tuning LLMs
  • Hands-on: Fine-tune an LLM for a specific task
     

• Beginners with basic python knowledge