Search Results for author:
Found 5 papers, 0 papers with code
Multi-Modal Cognitive Maps based on Neural Networks trained on Successor Representations
Cognitive maps, as represented by the entorhinal-hippocampal complex in the brain, organize and retrieve context from memories, suggesting that large language models (LLMs) like ChatGPT could harness similar architectures to function as a high-level processing center, akin to how the hippocampus operates within the cortex hierarchy.
Conceptual Cognitive Maps Formation with Neural Successor Networks and Word Embeddings
The human brain possesses the extraordinary capability to contextualize the information it receives from our environment.
Word class representations spontaneously emerge in a deep neural network trained on next word prediction
Strikingly, we find that the internal representations of nine-word input sequences cluster according to the word class of the tenth word to be predicted as output, even though the neural network did not receive any explicit information about syntactic rules or word classes during training.
Neural Network based Formation of Cognitive Maps of Semantic Spaces and the Emergence of Abstract Concepts
The neural network successfully learns the similarities between different animal species, and constructs a cognitive map of 'animal space' based on the principle of successor representations with an accuracy of around 30% which is near to the theoretical maximum regarding the fact that all animal species have more than one possible successor, i. e. nearest neighbor in feature space.
Neural Network based Successor Representations of Space and Language
We conclude that cognitive maps and neural network-based successor representations of structured knowledge provide a promising way to overcome some of the short comings of deep learning towards artificial general intelligence.
