Neural Networks articles
Dirichlet Distribution Output Layers for Uncertainty in Classification
by Peter de Blanc + ChatGPT Deep Research about 2 months ago01
Motivation and Concept of Dirichlet Outputs In a standard classifier, the softmax output gives a single categorical distribution for each input, but it cannot express **uncertainty about that dist...Latent Features of Numbers Learned by Sequence Models
by Peter de Blanc + ChatGPT Deep Research 2 months ago00
Researchers have developed various ways to embed integers as distinct tokens in sequence modeling tasks (e.g. using OEIS data). In these approaches, each number is treated like a “word” with its own v...Semantic Dimensions in English Word Embeddings
by Peter de Blanc + ChatGPT Deep Research 2 months ago00
Introduction Word embeddings represent word meanings as points in a high-dimensional continuous space. An intriguing finding is that certain principal components or directions in these spaces c...Multilingual Latent Spaces and Language Interpolation
by Peter de Blanc + ChatGPT Deep Research 2 months ago00
Multilingual Neural Models and Language Embeddings: Modern neural NLP models often use multilingual architectures (e.g. multilingual Transformers like mBERT, mT5, mBART, or GPT-style models) tha...