Artificial Intelligence Mind Map
This mind map provides a comprehensive overview of Artificial Intelligence (AI), detailing its key areas and concepts. It includes major subfields such as Machine Learning, which covers supervised, unsupervised, and reinforcement learning methods, and Theory, which encompasses foundational mathematical and statistical principles like probability theory and optimization. It also highlights the intersection of AI with Neuroscience, exploring brain-inspired models and techniques like EEG and fMR...
1. Machine Learning
1.1. Supervised
1.1.1. Regression
1.1.2. Classification
1.2. Unsupervised
1.2.1. Clustering
1.2.2. Dimensionality Reduction
1.2.3. Anomaly Detection
1.3. Reinforcement
1.3.1. Q-Learning
1.3.2. SARSA
1.3.3. Deep Reinforcement Learning
2. Theory
2.1. Probability Theory
2.2. Linear Algebra
2.3. Combinatorics
2.4. Optimization
2.4.1. Gradient Methods
2.4.2. Stochastic Methods
2.4.3. Genetic Algorithms
3. Neuroscience
3.1. EEG
3.2. fMRI
3.3. PET
3.4. Cortical Column
4. Neural Networks
4.1. Perceptron
4.2. Convolutional
4.3. Recurrent
4.4. Spiking Neural Networks
5. Robotics
5.1. Control Theory
5.2. ROS (Robot Operating System)
5.3. Autonomous Cars
6. Cognitive Models
6.1. Attention
6.2. Memory
6.2.1. Short-term
6.2.2. Long-term
6.2.3. Episodic
6.2.4. Semantic
6.3. Perception
6.3.1. Active Vision
6.3.2. Dynamic Routing
6.3.3. Action Selection
7. Knowledge Representation
7.1. Expert System
7.2. GOFAI (Good Old-Fashioned AI)
7.3. IBM Watson
7.4. Assistants (Siri)
7.5. Robot Sophia
8. Artificial General Intelligence (AGI)
8.1. Consciousness
8.2. Rationality
8.3. Reverse Brain Engineering
8.4. System (BrainMind)
8.5. Cognitive (Multi-brain)
9. AI Ethics
9.1. Existential Problems
9.2. Free Will Problem
9.3. Problem of Consciousness
9.3.1. Easy
9.3.2. Hard