Neural

systems inject rules written by humans. But what if a neural network could discover those rules itself? On this experiment, I extend a hybrid neural network with a differentiable rule-learning module that mechanically extracts...

Abstract datasets are extremely imbalanced, with positive rates below 0.2%. Standard neural networks trained with weighted binary cross-entropy often achieve high ROC-AUC but struggle to discover suspicious transactions under threshold-sensitive metrics. I propose a...

audio embeddings for music advice? Streaming platforms (Spotify, Apple Music, etc.) must have the power to recommend recent songs to their users. The higher the recommendations, the higher the listening experience. There are various ways...

of the AI boom, the pace of technological iteration has reached an unprecedented level. Previous obstacles now appear to have viable solutions. This text serves as an “NMT 101” guide. While introducing our...

in supply-chain planning has traditionally been treated as a time-series problem. Each SKU is modeled independently. A rolling time window (say, last 14 days) is used to predict tomorrow’s sales. Seasonality is captured, promotions are added,...

Introduction set is probably the most beautiful mathematical objects ever discovered, a fractal so intricate that regardless of how much you zoom in, you retain finding infinite detail. But what if we asked a...

Even networks long considered “untrainable” can learn effectively with a little bit...

Neural Network Regressor, we now move to the classifier version. From a mathematical viewpoint, the 2 models are very similar. In truth, they differ mainly by the interpretation of the output and the selection...