Towards Data Science

A Medium publication that shares various concepts, ideas, and coding resources.

International

English

Online/Digital

Outlet metrics

Domain Authority

Ranking

Global

#62865

United States

#38124

Computers Electronics and Technology/Programming and Developer Software

#867

Traffic sources

Monthly visitors

Articles

Circuit Tracing: A Step Closer to Understanding Large Language Models | Towards Data Science

2 weeks ago | towardsdatascience.com | Sudheer Singh

Over the years, Transformer-based large language models (LLMs) have made substantial progress across a wide range of tasks evolving from simple information retrieval systems to sophisticated agents capable of coding, writing, conducting research, and much more. But despite their capabilities, these models are still largely black boxes. Given an input, they accomplish the task but we lack intuitive ways to understand how the task was actually accomplished.
Master the 3D Reconstruction Process: A Step-by-Step Guide

3 weeks ago | towardsdatascience.com | Florent Poux

Privacy Preference CenterWhen you visit any website, it may store or retrieve information on your browser, mostly in the form of cookies. This information might be about you, your preferences or your device and is mostly used to make the site work as you expect it to. The information does not usually directly identify you, but it can give you a more personalized web experience. Because we respect your right to privacy, you can choose not to allow some types of cookies.
Forget About Cloud Computing. On-Premises Is All the Rage Again

1 month ago | towardsdatascience.com | Ari Joury

Ten years ago, everybody was fascinated by the cloud. It was the new thing, and companies that adopted it rapidly saw tremendous growth. Salesforce, for example, positioned itself as a pioneer of this technology and saw great wins. The tides are turning though. As much as cloud providers still proclaim that they’re the most cost-effective and efficient solution for businesses of all sizes, this is increasingly clashing with the day-to-day experience.
How LLMs Work: Reinforcement Learning, RLHF, DeepSeek R1, OpenAI o1, AlphaGo

1 month ago | towardsdatascience.com | Clara Chong |Srijanie Dey

Welcome to part 2 of my LLM deep dive. If you’ve not read Part 1, I highly encourage you to check it out first. Previously, we covered the first two major stages of training an LLM:Pre-training — Learning from massive datasets to form a base model. Supervised fine-tuning (SFT) — Refining the model with curated examples to make it useful. Now, we’re diving into the next major stage: Reinforcement Learning (RL).
How To Generate GIFs from 3D Models with Python

1 month ago | towardsdatascience.com | Florent Poux
Pandas Can’t Handle This: How ArcticDB Powers Massive Datasets

2 months ago | towardsdatascience.com | Ari Joury |Roger Noble

Python has grown to dominate data science, and its package Pandas has become the go-to tool for data analysis. It is great for tabular data and supports data files of up to 1GB if you have a large RAM. Within these size limits, it is also good with time-series data because it comes with some in-built support. That being said, when it comes to larger datasets, Pandas alone might not be enough.
Deep Dive into WebSockets and Their Role in Client-Server Communication

2 months ago | towardsdatascience.com | Clara Chong |Shreya Rao

Real-time communication is everywhere – live chatbots, data streams, or instant messaging. WebSockets are a powerful enabler of this, but when should you use them? How do they work, and how do they differ from traditional HTTP requests? This article was inspired by a recent system design interview – "design a real time messaging app" – where I stumbled through some concepts. Now that I’ve dug deeper, I’d like to share what I’ve learned so you can avoid the same mistakes.
11 Methods and Hardware Tools for 3D Scanning and Data Capture

2 months ago | towardsdatascience.com | Florent Poux

3D ToolsThe toolbox for data curation and 3D scanning: LiDAR, mesh, city models, 3D assets, hardware recommendations, photogrammetry, and AI methods for 3D reconstruction. I’ve been spending a lot of time lately thinking about the tools we use in 3D data processing and how they shape both our work and our thinking. I was reminded of a quote I love:“A good tool improves the way you work.
DeepSeek-V3 Explained 1: Multi-head Latent Attention

2 months ago | towardsdatascience.com | Shirley Li

Key architecture innovation behind DeepSeek-V2 and DeepSeek-V3 for faster inferenceThis is the first article of our new series “DeepSeek-V3 Explained”, where we will try to demystify DeepSeek-V3 [1, 2], the latest model open-sourced by DeepSeek. In this series, we aim to cover two major topics:Major architecture innovations in DeepSeek-V3, including MLA (Multi-head Latent Attention) [3], DeepSeekMoE [4], auxiliary-loss-free load balancing [5], and multi-token prediction training.
NLP Illustrated, Part 3: Word2Vec

2 months ago | towardsdatascience.com | Shreya Rao

An exhaustive and illustrated guide to Word2Vec with code!Welcome to Part 3 of our illustrated journey through the exciting world of Natural Language Processing! If you caught Part 2, you’ll remember that we chatted about word embeddings and why they’re so cool. Word embeddings allow us to create maps of words that capture their nuances and intricate relationships.