towardsdatascience.com

Leveraging Operations Research for Call Center Efficiency

Harnessing the power of efficient workforce optimization to drive...

Building Better ML Systems. Chapter 2: Taming Data Chaos.

Building Better ML Systems — Chapter 2: Taming Data ChaosAbout...

LangChain has added Cypher Search

With the LangChain library, you can conveniently generate Cypher queries, enabling an efficient retrieval of information from Neo4j.Image...

Testing Large Language Models like we test software

Testing language models (and prompts) like we test softwareTL;DR:...

The Return of the Fallen: Transformers for Forecasting

Photo by Aditya Vyas on UnsplashIntroducing a new transformer...

Interacting with large language models

Interacting with Large Language ModelsEnriching prompts to steer the model — explained for non-expertsLarge language models like GPT show astonishing capabilities for solving complex tasks like translation,...

How Well Do GPT Models Follow Prompts?

Part 2 of a study on generative AI usage and testingPhoto by Debby Hudson on UnsplashPrompt engineering is a special term from the NLP industry to describe the formulation of better questions for LLMs (large language...

Boosting image generation by intersecting GANs with Diffusion models

A recipe for stable and efficient image-to-image translationATME is a model in the GAN ∩ Diffusion class. Image generated using DALL·E 2.Visual Foundation Models (VFM) are at the core of cutting-edge technologies...

Can Data Science Find Bigfoot?

An analytical approach to tracking down one of the world’s most elusive cryptidsPhoto by Jon Sailer on UnsplashWatching Bigfoot researchers chasing — sometimes quite literally — circumstantial evidence,...

A/B Optimization with Policy Gradient Reinforcement Learning

A step by step visual explanation of the Policy Gradient methodChoose wisely! (Image created by the author with the help of Stable Diffusion Online)In this article, we will explore how policy gradient reinforcement...

Will Generative AI Replace the Need for Data Analysts?

Artwork Created by Author Using MidjourneyNo. But it will redefine the data analyst role.Since ChatGPT’s release in November of 2022, speculation has grown over whether or not the role of a data analyst could...

Top Data Science and Machine Learning Books to Read in 2023

Stay ahead of the curve: learn and grow with these distinguished data science and machine learning booksPhoto by Markus Spiske on UnsplashAs a recent Forbes publication highlighted, continuous learning is one of the...

Customizing your Cloud Based Machine Learning Training Environment — Part 2

Customizing your Cloud Based Machine Learning Training Environment — Part 2Additional solutions for increasing your development flexibilityPhoto by Murilo Gomes on UnsplashThis is the second part of a two-part...

Improve your Gradient Descent: The Epic Quest for the Optimal Stride

Techniques for Optimizing Step-Size/Learning Rate in Gradient Descent for Machine LearningImage by stokpic from PixabayContentsIntroductionMethod 1: Fixed Step SizeMethod 2: Exact Line SearchMethod 3: Backtracking...

Logistic Regression: Deceptively Flawed

When can large odds ratios and perfectly separated data bite you?Photo by Alvan Nee on UnsplashThis is a second part to a previous post on conceptual understanding of logistic regression:Logistic regression:...

How To Best Leverage OpenAI’s Evals Framework

Image licensed by author for commercial useKeys for evaluating LLMs using OpenAI EvalsThis blog is co-authored by Trevor LaVialeAccording to a recent survey, nearly half (43%) of data science and engineering teams are...

You Don’t Need Data Domains… Yet

Demystifying data mesh domainsYou don’t need data domains yet — Image courtesy of CastorThe data mesh paradigm advocates for the use of data domains as a way to partition data into meaningful groups. Domains...

How to Assess Recommender Systems

A deep dive on Evaluation Metrics FormulasImage Source. The image is free to use under the content licence of Pixabay.In recent articles, we have presented prominent recommender system algorithms that are widely...

Knowledge Graph Embeddings 101

A summary of knowledge graph embeddings (KGE) algorithmsImage Source. The image is free to use under the content licence of Pixabay.In our latest article of the series on How to design recommender systems based on...

Introduction to Knowledge Graph-Based Recommender Systems

A brief presentation of KG Recommender Systems FamiliesImage Source. The image is free to use under the content licence of Pixabay.Welcome back to the second article in our series about knowledge graph-based...

A better way to analyze feature release impact

Or — why naive “before-after” comparisons can drive bad product decisionsPhoto by author — using DALL-E 2A/B tests are the gold standard for estimating causal effects in product analytics. But in many...

Customizing your Cloud Based Machine Learning Training Environment — Part 1

Customizing Your Cloud Based Machine Learning Training Environment — Part 1How to leverage the power of the cloud without compromising development flexibilityPhoto by Jeremy Thomas on UnsplashCloud-based machine...

When CPU is faster than GPU — typical cases

When to Run Code on CPU and Not GPU: Typical CasesHow to choose the hardware to optimize the computation for your use casePhoto by Francesco Vantini on UnsplashWith rapidly advancing technologies like Artificial...

Tips and Tricks for Upgrading to PyTorch 2.0

What to look out for when moving to the all-new “Compiled Mode”Photo by Mohamed Nohassi on Unsplashby AuthorAny new release of an AI development framework, AI accelerator, or AI computing platform, brings with it...

Hugging Face Transformers Agent

Comparisons with 🦜🔗LangChain Agenthttps://medium.com/media/6024083523343b18395779f71658a293/hrefJust two days ago, 🤗Hugging Face released Transformers Agent — an agent that leverages natural language to...