Artificial Intelligece A-Z
This course teaches the fundamentals and advanced techniques of AI, including Q-Learning, Deep Learning, and Large Language Models. It covers implementing various AI models, such as A3C, PPO, and SAC, and explores Deep Convolutional Q-Learning. By the end, key AI concepts will be mastered and applied to solve real-world problems.
Skills for certificate:
Python
NumPy
Matplotlib
PyTorch
Jupyter Notebooks
Git
GitHub
Poetry
Computer Vision
Artificial Intelligence
Machine Learning
Deep Learning
Reinforcement Learning
Mathematics
Linear Algebra
Probability
Problem Solving
Project Management
Critical Thinking
Creativity
Adaptability
Object Oriented Programming
Algorithms
Data Science
Data Visualisation
Neural Networks
Intelligent Agents
Version Control
Artificial Intelligece A-Z
UC-db24645b-a4d3-4be7-95a6-ec0a051a9340
Description
This course teaches the fundamentals and advanced techniques of AI, including Q-Learning, Deep Learning, and Large Language Models. It covers implementing various AI models, such as A3C, PPO, and SAC, and explores Deep Convolutional Q-Learning. By the end, key AI concepts will be mastered and applied to solve real-world problems.
Learning Objectives
- Understanding the fundamentals of reinforcement learning
- Learning the Bellman Equation
- Exploring Markov Decision Processes
- Differentiating between policy and plan
- Grasping Q-Learning intuition and temporal difference
- Implementing Q-Learning for process optimization
- Mastering deep Q-Learning concepts
- Applying experience replay and action selection policies
- Implementing deep Q-Learning
- Understanding deep convolutional Q-Learning
- Learning eligibility trace in deep convolutional Q-Learning
- Implementing deep convolutional Q-Learning
- Mastering A3C concepts (Actor-Critic, Asynchronous, Advantage)
- Integrating LSTM layers in A3C
- Implementing A3C
- Building and training PPO and SAC models for self-driving cars
- Understanding large language models (LLMs)
- Exploring the components and history of LLMs
- Learning text generation and model architecture of LLMs
- Fine-tuning LLMs with Hugging Face
- Understanding deep learning concepts
- Exploring neuron functions and activation functions
- Learning how neural networks work and learn
- Applying gradient descent and backpropagation
- Mastering convolutional neural networks (CNNs)
- Understanding CNN operations, layers, and connections
- Summarizing deep learning with softmax and cross-entropy
- Implementing comprehensive Q-Learning techniques