Part

Data Science for Schools: Automate Timetabling with Python and OR-Tools, Part 1

A free, human-in-the-loop strategy to organise cover for workers absencesMatt Chapman·FollowPublished inTowards Data Science·10 min read·6 hours ago--SharePicture a faculty timetable:Looks pretty easy, right?Improper!Timetabling is a pain within the butt. It takes hours, and...

Hallucination Control: Advantages and Risks of Deploying LLMs as A part of Security Processes

Large Language Models (LLMs) trained on vast quantities of information could make security operations teams smarter. LLMs provide in-line suggestions and guidance on response, audits, posture management, and more. Most security teams are experimenting...

Productionize LLM RAG App in Django — Part I: Celery

Automate Pinecone Day by day Upsert Task with Celery and Slack monitoringIt’s been some time since my last LLM post and I’m excited to share that my prototype has been successfully productionized as Outside’s...

Suggestions for Getting the Generation Part Right in Retrieval Augmented Generation

Despite stellar leads to the generation tests, Claude 3’s accuracy declined in a retrieval-only experiment. Theoretically, simply retrieving numbers must be a better task than manipulating them as well — making this decrease in...

MS reveals a part of 'Customized Co-Pilot'… “Testing in progress… coming soon”

A few of the 'Customized Co-Pilot' that Microsoft (MS) announced in January has been released. In addition they announced that they plan to release a tool that permits anyone to create a customized...

Designing and Deploying a Machine Learning Python Application (Part 2)

As we haven’t quite solved the important thing problems, let’s dig in only a bit further before entering into the low-level nitty-gritty. As stated by Heroku:Web applications that process incoming HTTP requests concurrently make...

Understanding Latent Dirichlet Allocation (LDA) — A Data Scientist’s Guide (Part 2)

LDA Convergence Explained with a Dog Pedigree Model“What if my a priori understanding of dog breed group distribution is inaccurate? Is my LDA model doomed?”My wife asked.Welcome back to part 2 of the series,...

Courage to Learn ML: Demystifying L1 & L2 Regularization (part 3)

I’m glad you brought up this query. To get straight to the purpose, we typically avoid p values lower than 1 because they result in non-convex optimization problems. Let me illustrate this with a...

Recent posts

Popular categories

ASK DUKE