Machine Learning

What comes after Transformers? Google Research is proposing a new way to give sequence models usable long term memory with Titans and MIRAS, while keeping training parallel and inference close to linear. Titans is a concrete architecture that adds a deep neural memory to a Transformer style backbone. MIRAS is a general framework that views

Dimensionality reduction techniques like PCA work wonderfully when datasets are linearly separable—but they break down the moment nonlinear patterns appear. That’s exactly what happens with datasets such as two moons: PCA flattens the structure and mixes the classes together.  Kernel PCA fixes this limitation by mapping the data into a higher-dimensional feature space where nonlinear