5 papers
Contrastive Learning and Abstract Concepts: The Case of Natural Numbers
Daniel N. Nissani
Contrastive Learning (CL) has been successfully applied to classification and other downstream tasks related to concrete concepts, such as objects contained in the ImageNet dataset…
Unsupervisedly Learned Representations: Should the Quest be Over?
Daniel N. Nissani
After four decades of research there still exists a Classification accuracy gap of about 20% between our best Unsupervisedly Learned Representations methods and the accuracy rates…
Large Language Models Understanding: an Inherent Ambiguity Barrier
Daniel N. Nissani
A lively ongoing debate is taking place, since the extraordinary emergence of Large Language Models (LLMs) with regards to their capability to understand the world and capture the…
Contrastive Learning and the Emergence of Attributes Associations
Daniel N. Nissani
In response to an object presentation, supervised learning schemes generally respond with a parsimonious label. Upon a similar presentation we humans respond again with a label, bu…
An Unsupervised Learning Classifier with Competitive Error Performance
Daniel N. Nissani
An unsupervised learning classification model is described. It achieves classification error probability competitive with that of popular supervised learning classifiers such as SV…