Machine Learning

Learning discrete node embeddings. In this post, I want to present discrete graph node embeddings as part of my series on machine learning on graphs (part 1, part 2, part 3). In particular, it also discusses my last research paper on discrete node embeddings which was recently accepted for presentation at AAAI 23, the…

Evaluating Machine Learning models is a fundamental part of building reliable machine learning models. Evaluation ensures that the models effectively do the jobs they were built to do and also check for possible biases in our models. …

Deepak Ahire¹ and Shyam Shinde² 1. Software Engineer, Helpshift AI, Pune, India. Email: ahiredeepak20@gmail.com. ORCID: 0000-0002-9174-0797 2. Engineering Manager, Helpshift AI, Pune, India. Introduction There are a lot of blogs out there that talk about how to get onboarded with or integrate MLflow in your machine learning pipelines. But this blog…

Os dados se enganam ? Muitos dados são gerados, por conta dessa demanda vem surgindo varias área de pesquisa para que se possa obter o máximo de informação desses dados entre tanto quando se utilizar técnicas não adequadas para sua extração muitas das vezes ela pode ser ineficiente podendo leva…

Coming from an analytics & data science background, I used to see writing tests as something painful. I knew that it was important, but I never knew where to start and always procrastinated until the end of the project. …

A family of conversational neural language models developed by Google. Introduction In this blog, we will see what is LaMDA and what is the purpose of developing it. And we will also discuss the claims made by some people about LaMDA. What is LaMDA ? LaMDA, short for Language Model for Dialogue Applications was…

Usually during machine learning interviews after common questions there are project specific ones, so I have prepared a few must-knows for effective preparation and passing computer vision related interviews. Main tasks of computer vision classification — model learns what object is object detection — model finds object location (we can draw bounding box around it) …

認識資料飄移 (data distribution shift) 如何影響你上線的機器學習演算法 — 在資料圈工作一陣子之後發現，不論是 rule-based 的解法， ML 的解法，還是 DL 的解法，都時常會遇到，訓練的資料分佈和上線後的資料分佈不一致的情況，例如以下 : 自動駕駛車需要辨識紅綠燈，訓練資料都是晴天，但將模型上線時會遇到下雨，濃霧、沙塵甚至是月蝕。 電商推薦系統因為雙11，黑色星期五等短時間的大型促銷，促使使用者會買平常不會買的商品。 吃喝玩樂部落格因COVID-19，使用者的閱讀興趣改變 …