tgakathunderr/BIM-2
Biologically inspired language model using Jaccard Surprise as its only training signal. No backprop. No GPU. Online Hebbian learning from corrections. Two-layer cortex with apical feedback. Runs on CPU under 200MB.
GitHub repository with 21 stars and 1 forks.
Language: Python
Topics: ai, artificial-intelligence, artificial-neural-networks, biologically-inspired, computational-neuroscience, cortical-learning, cpu-native, hebbian-learning, htm, jaccard