Semantic similarity increases with similar semantic units of similar semantic contexts in the monolingual word alignment. | Continue reading
Wrap you resource creation and closure into context manager with-statement and catch exceptions there. | Continue reading
Cross-attention is a way to merge two embedding sequences e.g. image with text. | Continue reading
Reducing compute by combining RNN with self-attention from Transformer architecture. | Continue reading
Using attribute-specific subspaces for image manipulation retrieval, outfit completion, conditional similarity retrieval. | Continue reading
Reducing training flops 4x by GAN-like discriminative task compared to RoBERTa-500K | Continue reading
Reducing computational costs by differentiably dropping memorized embeddings from self-attention context. | Continue reading
How to version data using Quilt data for Python on AWS S3. | Continue reading
Audio Word2vec - Quantize phonemes, transform, GAN the text. | Continue reading
Learning to code by growing function library, fantasising coding tasks, and training neural search. | Continue reading
Proportional–integral–derivative controller calculates feedback to reduce the error in the next step. | Continue reading
Diminishing returns with a budget constraint in problems of coverage and results diversification. | Continue reading
Take a tour of the surprising merge of a modern and soviet era design on a Prague’s public square with this photo album. | Continue reading
To improve your apartment acoustics while not making it too ugly, place cheap thin acoustic wall panels behind an art, such as wall-mounted world map. | Continue reading
To serve ML models, this post compares major open source platforms BentoML and Cortex. | Continue reading