Completed
Summary
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Logical Neural Networks: Unifying Statistical and Symbolic AI
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Logical Neural Networks
- 3 Neuro-symbolic methods so far
- 4 Neuro-symbolic methods: another category
- 5 Original (McCulloch and Pitts 1943) neuron as logic gate
- 6 Weighted neuron (perceptron, 1958) as logic gate
- 7 Differentiable neuron (MLPs, deep learning) as logic gate
- 8 b. Constrained differentiable neuron (LNN) as logic gate
- 9 a. Neuron (LNN) as real-valued logic gate
- 10 a. Neural network inference as logical reasoning
- 11 a. Data and learning
- 12 7b. Data and learning
- 13 Equivalence between neural networks and symbolic logic
- 14 Comparison to other common neuro-symbolic ideas
- 15 Use case: Knowledge base question answering (KBQA)
- 16 KBQA: Why it challenges default Al (end-to-end deep learning)
- 17 KBQA: an approach via understanding
- 18 Making the model & inference process human-understandable
- 19 Learning to reason
- 20 Logical rule induction (ILP)
- 21 Optimization/learning
- 22 Reinforcement learning
- 23 Policy induction via rule learning
- 24 AGI: Bengio-Marcus Desiderata
- 25 Ongoing directions
- 26 Philosophical shift
- 27 Summary
