Intermediate Attention

But what is a neural network? | Deep learning chapter 1

The Essential Main Ideas of Neural Networks

Transformers Explained - How transformers work

Transformer Neural Networks - EXPLAINED! (Attention is all you need)

Illustrated Guide to Transformers Neural Network: A step by step explanation

Natural Language Processing: Crash Course AI 7

More and more evidence has demonstrated that graph representation learning especially graph neural networks (GN Ns) has tremendously facilitated computational tasks on graphs including both node-focused and graph-focused tasks. The revolutionary advances brought by GN Ns have also immensely contributed to the depth and breadth of the adoption of graph representation learning in real-world applications. For the classical application domains of graph representation learning such as recommender systems and social network analysis, GN Ns result in state-of-the-art performance and bring them into new frontiers. Meanwhile, new application domains of GN Ns have been continuously emerging such as combinational optimization, physics, and healthcare. These wide applications of GN Ns enable diverse contributions and perspectives from disparate disciplines and make this research field truly interdisciplinary.In this course, I will start by talking about basic graph data representation and concepts like node data, edge types, adjacency matrix and Laplacian matrix etc. Next, we will talk about broad kinds of graph learning tasks and discuss basic operations needed in a GNN: filtering and pooling. Further, we will discuss details of different types of graph filtering (i.e., neighborhood aggregation) methods. These include graph convolutional networks, graph attention networks, confidence GC Ns, Syntactic GC Ns and the general message passing neural network framework. Next, we will talk about three main types of graph pooling methods: Topology based pooling, Global pooling and Hierarchical pooling. Within each of these three types of graph pooling methods, we will discuss popular methods. For example, in topology pooling we will talk about Normalized Cut and Graclus mainly. In Global pooling, we will talk about Set2Set and Sort Pool. In Hierarchical pooling, we will talk about diff Pool, g Pool and SAG Pool. Next, we will talk about three unsupervised graph neural network architectures: Graph

Welcome to the 10 Days of Prompt Engineering, Generative AI, and Data Science Course Get hands-on with Prompt Engineering, Generative AI, and Data Science in just 10 days. I’m Diogo, and I’ve structured this course to take you from basics to advanced topics quickly. We’ll cover live sessions, hands-on labs, and real-world projects—all in 14 hours and 30 minutes of published video content. You’ll also receive lifetime updates so your learning never goes stale.You will build a portfolio of project on topics like:Prompt Engineering Fundamentals: Understand transformers, attention mechanisms, and how to structure prompts for optimal performance.Generative AI Workflows: Master tools like Google Colab, Jupyter Notebook, LM Studio, and learn how to fine-tune system messages and model parameters.OpenAI API for Text & Images: Integrate the OpenAI API into Python projects, explore parameters for better text generation, and tap into image generation (coming soon).Machine Learning with XG Boost & Random Forest: Explore advanced ML topics, including parameter tuning, SHAP values, and real-world approaches to customer satisfaction modeling.AI Agents with CrewAI: Dive into the next wave of AI automation (coming in Q1 2025).COURSE BREAKDOWN Introduction Meet your instructor, download course materials, set up your environment (Google Colab, Jupyter Notebook, RStudio).Preview the core projects we’ll tackle.Day 1 – Basics of Prompt Engineering Learn about transformers, attention, and chain-of-thought prompting.Experiment with LM Studio to practice

Welcome to your transformative journey into the world of artificial intelligence and deep learning! This isn't just another course – it's your comprehensive AI education blueprint that delivers the equivalent content of five premium courses bundled into one power-packed learning experience. After six months of intensive research, we've created a program that will transform you from a complete beginner into a confident AI practitioner.What You'll Learn Master fundamental principles of machine learning and advance to transformer models, attention mechanisms, and generative AI Build your first neural networks using PyTorch and TensorFlow Explore natural language processing (NLP) with GPT-4, Claude, and other large language models (LL Ms)Develop AI agents using LangChain that can reason, plan, and execute complex tasks Create Retrieval-Augmented Generation (RAG) systems with vector databases and embeddings Master prompt engineering techniques for optimal AI results Implement computer vision applications using convolutional neural networks (CNNs)Apply reinforcement learning principles to create self-improving AI agents Design AI automation strategies that streamline workflows and reduce costs Understand AI ethics and responsible development practices Learn model fine-tuning techniques for specific domains Deploy AI solutions using AWS, Google Cloud