IO-aware batched K-Means for Apple Silicon, ported from Flash-KMeans (Triton/CUDA) to pure MLX. 500K points, 128 dimensions, K=1000 clustered in 0.76s on M3 Ultra -- 160x faster than sklearn. Uses ...

Dynamic interactions between brain regions, either during rest or performance of cognitive tasks, have been studied extensively using a wide variance of methods. Although some of these methods allow ...

Knowing what people are talking about in near real-time is incredibly powerful. This type of information can inform campaigns, brand strategy and product innovation. The standard way to gather this ...

For solving tasks such as recognizing a song, answering a question, or inverting a sequence of symbols, cortical microcircuits need to integrate and manipulate information that was dispersed over time ...

This repository contains the source code of some of the experiments conducted for our paper "Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation", published in TRO in 2021.

Thompson Sampling is an algorithm that can be used to analyze multi-armed bandit problems. Imagine you're in a casino standing in front of three slot machines. You have 10 free plays. Each machine ...

Most linear algebra courses start by considering how to solve a system of linear equations. \[ \begin{align} a_{0,0}x_0 + a_{0,1}x_0 + \cdots a_{0,n-1}x_0 & = b_0 ...