611 📠 Machine Learning
Machine Learning ist das Teilgebiet der KI, das Systeme aus Daten lernen lässt — ohne explizite Programmierung jedes Verhaltens.
→ Übergeordnet: 610 🤖Artificial Intelligence, Künstliche Intelligenz
🧩 Kernthemen
Lernparadigmen
Neuronale Netze & Deep Learning
- A deep learning framework for neuroscience
- Gradient Descent · Gradient Backpropagation
- Regularizers · prevent overfitting while using many parameters
- Perceptron
Transformer & LLMs
- Attention is All You Need · Attention Mechanism
- Chain-of-Thought Reasoning · Large Concept Models (LCM)
- DSPy framework · Prompt Engineering
Reinforcement Learning
- Temporal Difference Reinforcement Learning
- Q-Function · Bellman Equation
- Maximum entropy off-policy RL with the SAC algorithm
- You Only Live Once, Single Life Reinforcement Learning
Evaluation & Konzepte
Neuroscience × ML
- Machine Learning for Cognitive Computational Neuroscience
- A deep learning framework for neuroscience
- Molecular generative models
📋 Alle Notizen
- A deep learning framework for neuroscience
- A Vision-Language-Action Flow Model for General Robot Control
- AI Agents
- Assignment 1 Neurodynamics
- Attention is All You Need
- Chain-of-Thought Reasoning
- Cheatsheet_Paper-Transformers-Search
- Claude Code Befehle
- Constraint Satisfaction Problems
- Control of Mobile Robots Using the Soar Cognitive Architecture (SOAR, 2009)
- cul-de-sac obstacles
- Das Model Unser
- DSPy framework
- Entropy
- Gabor Filter
- Good Prompts
- Imitation Learning
- Implementing Artificial Neural Networks with TensorFlow
- Information Gain
- Large Concept Models (LCM)
- Machine Learning for Cognitive Computational Neuroscience
- Maximum entropy off-policy RL with the SAC algorithm
- Methods of AI Seminar
- ML for NLP
- Molecular generative models
- Neuralink Artikel md für website
- Neurolink Update Summer 2025
- NP-complete
- Paper Review Genetic Algorithms
- PDDL and STRIPS
- Perceptron
- prevent overfitting while using many parameters
- Prompt Engineering
- Q-Function
- RCC-8
- Regularizers
- Reverse Engineering
- Reward Rover
- Simulated Annealing
- Stochastic Diffusion Search
- Supervised Learning
- Temperature in neighbour selection
- Temporal Difference Reinforcement Learning
- Tool - Reinforcement Learning Game
- Unsupervised Learning
- Webgrid Neurolink-Game
- What is an AI?
- What the SOAR Algorithm teaches us about cognitive abilities in AIs
- Wie Artificial Intelligence funktioniert
- Wir finde ich die richtigen Parameter in Simulated Annealing?
- You Only Live Once, Single Life Reinforcement Learning
- Zero-shot adaptation
Superlink: 610 🤖Artificial Intelligence, Künstliche Intelligenz