bookmarks (hide)68
- Scientists used machine learning to reveal new scientific knowledge hidden in old research papers.
- In mathematics, the Wasserstein or Kantorovich–Rubinstein metric or distance is a distance function defined between probability distributions on a given metric space M {\displaystyle M} M. Intuitively, if each distribution is viewed as a unit amount of "dirt" piled on M {\displaystyle M} M, the metric is the minimum "cost" of turning one pile into the other, which is assumed to be the amount of dirt that needs to be moved times the mean distance it has to be moved. Because of this analogy, the metric is known in computer science as the earth mover's distance.
- TLDR — Extractive question answering is an important task for providing a good user experience in many applications. The popular Retriever-Reader framework for QA using BERT can be difficult to scale…
- In this post, Phillip talks through the challenges & pitfalls of LLMs we faced when building our Query Assistant - and that you too may face.
- Can't remember what is precision and recall (sensitivity)? Why accuracy is not enough? Read the explanation with an example with a confusion matrix.
- We introduce Vicuna-13B, an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. Preliminary evaluation using GPT-4 as a judge shows Vicuna-13B achieves more than 90%* quality of OpenAI ChatGPT and Google Bard while outperforming other models like LLaMA and Stanford Alpaca in more than 90%* of cases. The cost of training Vicuna-13B is around $300. The code and weights, along with an online demo, are publicly available for non-commercial use.
- Kedro versioned datasets can be mixed with incremental and partitioned datasets [ �� Unsure what kedro is? Check out this post. This was a question presented to
- In previous articles, we explored how Snowpark Container Services can open doors to a complete data stack running solely on Snowflake (here) and showcased all essential tools Snowflake provides to achieve this (here). Now, it’s time to dive into the practical side of things. This article will guide you through a step-by-step implementation of running dbt in Snowpark Container Services, covering everything from setup and containerisation all the way to scheduling and monitoring. If you’re trying to create a simple containerised dbt setup, this guide will help you put all theory into action!
- Facebook Research open sourced a great project recently – fastText, a fast (no surprise) and effective method to learn word representations and perform text classification. I was curious about comparing these embeddings to other commonly used embeddings, so word2vec seemed like the obvious choice, especially considering fastText embeddings are an extension of word2vec.
publications
(hide)163
This list of posts may not be accurate to recent changes. If you want accurate posts, but with limited sorting follow this link.
- (2025)
- (2024)
- (2024)
- The Twelfth International Conference on Learning Representations, (2024)
- (2024)
- (2024)
- Forty-first International Conference on Machine Learning, (2024)
- (2024)
- (November 2023)
- 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), page 1-6. IEEE, (July 2023)
