@towardsdatascience@me.dm
@towardsdatascience@me.dm avatar

towardsdatascience

@towardsdatascience@me.dm

A Medium publication sharing concepts, ideas, and codes. Share your insights and projects with our global audience: http://bit.ly/write-for-tds.

This profile is from a federated server and may be incomplete. Browse more on the original instance.

towardsdatascience, to random
@towardsdatascience@me.dm avatar

In a comprehensive, hands-on guide, Agustinus Nalwan leverages the power of LLMs to enhance the quality of document context retrieved for direct-answer generation in your RAG setup. https://buff.ly/4aUKeik

towardsdatascience, to random
@towardsdatascience@me.dm avatar

Discover the BiTCN model for multivariate time series forecasting, explore its architecture, and implement it in Python - 🖋️ by Marco Peixeiro https://buff.ly/4aZjjBP

towardsdatascience, to random
@towardsdatascience@me.dm avatar

In part two of her excellent series on computer simulations for product analysts, Mariya Mansurova provides a thorough, hands-on guide to using bootstrap for observations and A/B tests. https://buff.ly/3QmGTjG

towardsdatascience, to random
@towardsdatascience@me.dm avatar

By taking a close look at the evolution of human intelligence, could we perhaps gain a better understanding of AI's potential — and limitations?

Stephanie Shen's latest deep dive explores one of the most fascinating questions at the intersection of neuroscience and technology. https://buff.ly/3JEDtVV

towardsdatascience, to random
@towardsdatascience@me.dm avatar

Are we beginning to see a meaningful shift away from proprietary models to smaller open-source foundation models? Leonie Monigatti shares a thoughtful panoramic overview of current trends in the GenAI ecosystem. https://buff.ly/3wkXJIQ

towardsdatascience, to random
@towardsdatascience@me.dm avatar

"This article describes recent results on dealing with what we call “trial-and-error” tasks and explain how optimal decisions can be derived by modeling the system as a continuous-time Markov chain, aka Markov Jump Process."

Read more from Nikolaus Correll's post: https://buff.ly/3wvLZDa

towardsdatascience, to random
@towardsdatascience@me.dm avatar

"Besides the familiar learning rate lr and momentum parameters, there are several other that have stark effects on neural network training. In this article we’ll visualize the effects of these parameters on a simple ML objective with a variety of loss functions." by P.G. Baumstarck https://towardsdatascience.com/visualizing-gradient-descent-parameters-in-torch-332a63d1e5c5

towardsdatascience, to random
@towardsdatascience@me.dm avatar

It all started with GPT having an input context window of 512 tokens. After only 5 years the newest LLMs are capable of handling 1M+ context inputs. Where’s the limit?

by Krzysztof K. Zdeb https://buff.ly/4bfsQEM

towardsdatascience, to random
@towardsdatascience@me.dm avatar

What’s The Story With HNSW? Exploring the path to fast nearest neighbour search with Hierarchical Navigable Small Worlds by Ryan McDermott https://buff.ly/49s367w

towardsdatascience, to random
@towardsdatascience@me.dm avatar

"There are some indications that the hype around ES was too much compared to reality, but this is usual in new fields, as they need some attention and funding in order to get traction."

What Happened With Expert Systems? by Rafe Brena, Ph.D. https://towardsdatascience.com/what-happened-with-expert-systems-aad399eab180

towardsdatascience, to random
@towardsdatascience@me.dm avatar

You'll want to carve out some time this weekend to read Mike Cvet's new deep dive: a thorough, accessible, and actionable guide to temperature scaling and beam search text generation in LLMs. https://towardsdatascience.com/temperature-scaling-and-beam-search-text-generation-in-llms-for-the-ml-adjacent-21212cc5dddb

towardsdatascience, to random
@towardsdatascience@me.dm avatar

Catch up with our latest math and stats must-reads — highlights include articles by Merete Lutz on N-of-1 trials, Bradley Stephen Shaw on the shelf life of time series forecasts, Tahreem Rasul on building a math app with LangChain agents, Sachin Date on the central limit theorem (and candy!), and Conor O'Sullivan on visualizing linear regressions effectively. https://buff.ly/3WfvvtC

towardsdatascience, to random
@towardsdatascience@me.dm avatar

Dive into AlexNet, the first modern CNN, understand its mathematics, implement it from scratch, and explore its applications by Cristian Leo https://buff.ly/49END39

towardsdatascience, to random
@towardsdatascience@me.dm avatar

When existing movie recommendation systems didn't deliver the right suggestions, Ed Izaguirre decided to build a better one himself.

His new post details the process of creating a functional RAG system with a self-querying retriever in LangChain. https://buff.ly/3QfSHnV

towardsdatascience, to random
@towardsdatascience@me.dm avatar

"Simulation is a powerful tool in the data science tool box. In this article, we’ll talk about how simulating systems can help us formulate better strategies and make better decisions."

Simulated Data, Real Learnings : Simulating Systems by Jarom Hulet https://buff.ly/3U2Po4l

towardsdatascience, to random
@towardsdatascience@me.dm avatar

In this article, Sandi Besen explores the situations in which Retrieval Augmented Generation (RAG) excels and those in which it falls short: https://buff.ly/3VXob5X

towardsdatascience, to random
@towardsdatascience@me.dm avatar

Visualizing My Data Science Job Search - Reflections from a humbling journey trying to find a job in 2023 by Erin Wilson https://buff.ly/3waDgq2

towardsdatascience, to random
@towardsdatascience@me.dm avatar

From giving back to the community to gaining valuable experience, there are many benefits to contributing to open source projects. Mike Clayton shares key takeaways from his recent experience of fixing bug in the ever-popular Pandas library. https://buff.ly/3QayfEJ

towardsdatascience, to random
@towardsdatascience@me.dm avatar

In a patient, practical explainer, Janna Lipenkova unpacks the principles that ensure product teams design a solid relationships between LLM-based tools and user experience. https://buff.ly/4aJyAqt

towardsdatascience, to random
@towardsdatascience@me.dm avatar

What is the Python LEGB Rule? Why It is Important?

The namespaces and resolution order help to improve the performance and robustness of Python programming

🖋️ by Christopher Tao https://towardsdatascience.com/what-is-the-python-legb-rule-why-it-is-important-1fdcfecfd62f

towardsdatascience, to random
@towardsdatascience@me.dm avatar

In a detailed, action-oriented deep dive, Mariya Mansurova outlines task-specific approaches for scenario forecasting. https://towardsdatascience.com/practical-computer-simulations-for-product-analysts-90b5deb6a54e

towardsdatascience, to random
@towardsdatascience@me.dm avatar

"In this article, I will test four different models (7B, 8x7B, 22B, and 8x22B, with and without a “Mixture of Experts” architecture), and we will see the results." by Dmitrii Eliuseev https://buff.ly/3W4E5v9

towardsdatascience, to random
@towardsdatascience@me.dm avatar

The Math Behind ‘The Curse of Dimensionality’ - Dive into the “Curse of Dimensionality” concept and understand the math behind all the surprising phenomena that arise in high dimensions. by Maxime Wolf https://buff.ly/446oIUW

towardsdatascience, to random
@towardsdatascience@me.dm avatar

"Creating training data for image segmentation tasks remains a challenge for individuals and small teams. And if you are a student researcher like me, finding a cost-efficient way is especially important. In this post, I will talk about one solution that I used in my capstone project where a team of 9 people successfully labeled 400+ images within a week." by Alison Yuhan Yao https://buff.ly/44oXUQh

towardsdatascience, to random
@towardsdatascience@me.dm avatar

Leveraging her own fitness data, Merete Lutz explores the potential interplay of sleep quality and alcohol consumption, and the broader benefits of N-of-1 trials. https://buff.ly/49QD6BX

  • All
  • Subscribed
  • Moderated
  • Favorites
  • •
  • megavids
  • khanakhh
  • ngwrru68w68
  • mdbf
  • tacticalgear
  • Youngstown
  • rosin
  • slotface
  • Durango
  • kavyap
  • everett
  • thenastyranch
  • InstantRegret
  • DreamBathrooms
  • JUstTest
  • magazineikmin
  • anitta
  • GTA5RPClips
  • modclub
  • cisconetworking
  • cubers
  • osvaldo12
  • ethstaker
  • provamag3
  • normalnudes
  • Leos
  • tester
  • lostlight
  • All magazines
    •