Speed Comparison — Introduction A wide range of audio data is available in the real world: speech, animal sounds, instruments — you name it. No wonder audio-based machine learning is a niche application across many sectors and industries. Compared to other types of data, audio data typically requires lots of time-consuming and resource-demanding processing…

Simple techniques for creating better, domain-specific LLMs — Large language models (LLMs) are incredibly-useful, task-agnostic foundation models. But, how much can we actually accomplish with a generic model? These models are adept at solving common natural language benchmarks that we see within the deep learning literature. But, using LLMs practically usually requires that the model be taught new…

回归分析和反事实解释 - 解释是由Microsoft设计的可解释的机器学习库，目的是使机器学习模型更加容易理解，并且对人类的解释开放。在与业务利益相关者进行沟通时，这具有特殊的价值，他们在许多情况下是非技术的，并试图了解发现的业务影响……

A Large-Scale Data Analysis of the Performance Costs of Training Disruptions when Preparing for the Marathon — TLDR; More than 50% of runners experience at least a 7-day break from running when training for a marathon. Longer training disruptions (≥7 days) also occur frequently. But there is hope because even a long disruption does not have to ruin your marathon. However, disruptions do come with a cost, and…

Get data, train ViT, minimize problem; and way too overkill — What happens when a data scientist gets a riddle in form of a box? Of course he will (try) approach it as a data problem. In this article I will describe the whole process, and to be honest, it was not as easy as I thought. …