Foundation of AI, ML, NN and GenAI + Capstone Project

Learn how machine learning uses data to identify patterns, build models to make predictions, and generalize from labeled and unlabeled data, including supervised, unsupervised, and reinforcement learning.

Explore supervised, unsupervised, and reinforcement learning and how algorithms create models, covering linear regression, logistic regression, Naive Bayes, SVM, and KNN.

Learn how a machine learning model, a function learned from data through a training algorithm, predicts outcomes from features and labels, with training/test data split for evaluation.

Evaluate machine learning models with metrics such as accuracy, precision, recall, F1, MSE, and RMSE, then follow the ML workflow from problem definition to deployment and explore career paths.

Build and deploy a supervised machine learning model in Python using a diabetes dataset, training with logistic regression and evaluating via a confusion matrix and accuracy.

Explore how neural networks learn via forward and backward propagation, activation functions, and loss optimization, enabling deep learning on unstructured data with GPUs and popular libraries.

Explore the core neural network architectures, including fully connected networks, CNNs, RNNs, and autoencoders, and learn how convolution, pooling, ReLU, and latent space drive vision and language tasks.

Explore generative ai and its models, including transformers, GANs, VAEs, and diffusion. See how gen ai creates text, images, video, and code with tools like ChatGPT, Claude, Gemini, and Grok.

Explore GenAI models and how tools talk to them via APIs from OpenAI, Gemini, and cloud. Compare transformer-based generation across text, image, audio, and code; explain encoder and decoder roles.

GenAI rises in popularity by leveraging vast data and large language models to transform healthcare, finance, and content creation, boosting efficiency and creativity with AI copilots and synthetic data.

Explore how GenAI models create new content with autoencoders, variational autoencoders, GANs, and diffusion models, including encoder roles, mean and variance in latent space, and denoising.

Discover how transformer architecture revolutionizes ai by efficiently handling long-range context with tokenization, embeddings, and positional encoding, enabling fast, scalable language models.

Explore how tokenization based on language vocabulary, embeddings including positional embedding, and encoder-decoder blocks with self-attention and multi-head attention create semantic representations in transformers.

Explore large language models and small language models, and how fine tuning adapts them for specific tasks, using transformer architectures trained on massive data to generate human-like text for chatbots.

Explore top LLM makers and AI labs, including OpenAI, Anthropic, and Google Gemini, and see how ChatGPT, Codex, Claude, and Imagen power modern AI across platforms.

Understand how AI agents perceive their environment, reason, and autonomously act to achieve goals using large language models (LLMs), tools, and memory, guided by instructions and planning.

Explore ethical and responsible ai principles, including fairness, reliability and safety, privacy and security, inclusiveness, transparency, and accountability, while examining challenges like deepfakes, bias, hallucination, and intellectual property concerns.