6 papers
Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces
Michael Pichat, William Pogrund, Paloma Pichat +6
The polysemantic nature of synthetic neurons in artificial intelligence language models is currently understood as the result of a necessary superposition of distributed features w…
Neuropsychology and Explainability of AI: A Distributional Approach to the Relationship Between Activation Similarity of Neural Categories in Synthetic Cognition
Michael Pichat, Enola Campoli, William Pogrund +7
We propose a neuropsychological approach to the explainability of artificial neural networks, which involves using concepts from human cognitive psychology as relevant heuristic re…
Neuropsychology of AI: Relationship Between Activation Proximity and Categorical Proximity Within Neural Categories of Synthetic Cognition
Michael Pichat, Enola Campoli, William Pogrund +7
Neuropsychology of artificial intelligence focuses on synthetic neural cog nition as a new type of study object within cognitive psychology. With the goal of making artificial neur…
Using meaning instead of words to track topics
Judicael Poumay, Ashwin Ittoo
The ability to monitor the evolution of topics over time is extremely valuable for businesses. Currently, all existing topic tracking methods use lexical information by matching wo…
HTMOT : Hierarchical Topic Modelling Over Time
Judicael Poumay, Ashwin Ittoo
Over the years, topic models have provided an efficient way of extracting insights from text. However, while many models have been proposed, none are able to model topic temporalit…
A Comprehensive Comparison of Word Embeddings in Event & Entity Coreference Resolution
Judicael Poumay, Ashwin Ittoo
Coreference Resolution is an important NLP task and most state-of-the-art methods rely on word embeddings for word representation. However, one issue that has been largely overlook…