Translating Terms with LLMs (GPT and Vertex AI/Google Bard)
Published in · 6 min read · 1 day ago Photo by Mojahid Mottakin on Unsplash Can LLMs like ChatGPT accurately make translations better than humans? What options of LLMs … Read more
data_admin
The Olympics of AI: Benchmarking Machine Learning Systems
How do benchmarks birth breakthroughs? Published in · 13 min read · Just now You can’t improve what you don’t measure. — Peter Drucker The Olympic rings. Image created by … Read more
Advanced Python: Functions
Published in · 11 min read · Aug 1
How to Talk About Data and Analysis to Non-Data People
A step-by-step tutorial for data professionals Published in · 14 min read · 1 hour ago In my recent articles, I noted that a significant challenge for many companies today … Read more
Creating Confidence Intervals for a Linear Model in R Using Base R and the Iris Dataset
Linear regression is a fundamental statistical technique used to model the relationship between a dependent variable and one or more independent variables. While fitting a linear model is relatively straightforward … Read more
Exploring Numexpr: A Powerful Engine Behind Pandas
Enhancing your data analysis performance with Python’s Numexpr and Pandas’ eval/query functions Published in · 10 min read · Just now Use Numexpr to help me find the most livable … Read more
Five Practical Applications of the LSTM Model for Time Series, with Code
How to implement an advanced neural network model in several different time series contexts Published in · 11 min read · 3 hours ago Photo by Andrew Svk on Unsplash … Read more
Host Hundreds of NLP Models Utilizing SageMaker Multi-Model Endpoints Backed By GPU Instances
Integrate Triton Inference Server With Amazon SageMaker Published in · 7 min read · 4 hours ago Image from Unsplash In the past we’ve explored SageMaker Multi-Model Endpoints (MME) as … Read more
rOpenSci News Digest, September 2023
Dear rOpenSci friends, it’s time for our monthly news roundup! You can read this post on our blog. Now let’s dive into the activity at and around rOpenSci! rOpenSci HQ … Read more
XGBoost: How Deep Learning Can Replace Gradient Boosting and Decision Trees — Part 2: Training
Published in · 6 min read · Just now Photo by Simon Wilkes on Unsplash In a previous article: you have learned about rewriting decision trees using a Differentiable Programming … Read more
Extracting text from PDF files with Python: A comprehensive guide
Now that we have all the components of the code ready let’s add them all up to a fully functional code. You can copy the code from here or you … Read more
How to Build an LLM from Scratch
Historically (i.e. less than 1 year ago), training large-scale language models (10b+ parameters) was an esoteric activity reserved for AI researchers. However, with all the AI and LLM excitement post-ChatGPT, … Read more
Generative AI on Research Papers Using Nougat Model
Doing cool things with Data! Published in · 9 min read · 1 day ago Photo by Dan Dimmock on Unsplash Recent advances in large language models (LLMs) like GPT-4 … Read more
LLM Output Parsing Function Calling vs. LangChain
Creating tools with LLMs requires multiple components, such as vector databases, chains, agents, document splitters, and many other new tools. However, one of the most crucial components is the LLM … Read more
Two New Papers Analyze in Detail the Protein Universe Unveiled by AlphaFold 2’s 200 Million Models
And they had to create new tools to handle such large volume of protein structural models Published in · 7 min read · 6 hours ago One of the resources … Read more
Simulate interruptions in your Spot Fleet directly from the Amazon EC2 Console
You can now inject random Amazon EC2 Spot Instance interruptions into your Spot Fleets directly from the Amazon EC2 console. In 2022, we launched the ability for you to use … Read more
Exploring Large-scale Raster Population Data
Image by the author. Visualizing geospatial population data across multiple scales using Python: global, country, and urban-level data Published in · 9 min read · 1 hour ago I have … Read more
Can ChatGPT solve knapsack problems?
Solving operations research (OR) problems with ChatGPT Published in · 10 min read · Just now Photo by Jakob Owens on Unsplash Ever since the emergence of ChatGPT, I’ve been … Read more
How to Choose the Right Data Visualization Strategy for Your Project
Published in · 3 min read · Just now New tools and packages come and go, but the basic grammar of data visualization remains incredibly resilient to trends: at the … Read more
Confidence Intervals in Election Polling: Understanding the Uncertainty of Political Forecasting
Election polls play a crucial role in predicting the outcome of elections and shaping public opinion. However, it’s important to understand that the results of any single poll should be … Read more
Bugs in Python? Pdb To the Rescue!
PYTHON PROGRAMMING Is the Pdb debugger worth learning and using? Published in · 13 min read · Just now Debugging helps you learn from your failures. Photo by Brett Jordan … Read more
Entity Resolution: Identifying Real-World Entities in Noisy Data
Each record represents a song having attributes such as artist, title, album, year, etc (You can find field descriptions in this link). CID is cluster ID and the records having … Read more
AI Music Source Separation: How it Works and Why It Is So Hard
Source Separation AI, explained Published in · 9 min read · Just now Image by Author. What is Source Separation? In the field of signal processing, source separation describes the … Read more
Google Pub/Sub to BigQuery the Simple Way
A hands-on guide to implementing BigQuery Subscriptions in Pub/Sub for simple message and streaming ingestion Published in · 8 min read · 4 hours ago Google’s latest planet-scale data warehouse … Read more
Parallel raster processing in stars
[view raw Rmd] Summary: Prediction on large datasets can be time-consuming, but with enough computing power, this task can be parallelized easily. Some algorithms provide native multithreading like predict() function … Read more
The Super League: Tournament Blood Bowl online
(Photo by Erik Cats) Yet another Blood Bowl post! If you don’t know about Blood Bowl and/or FUMBBL, See my previous blog posts on Blood Bowl for more background and … Read more
Estimating Total Experimentation Impact
How to control for false-discovery and selection biases when measuring your organization’s total impact Published in · 16 min read · Just now Photo by CHUTTERSNAP on Unsplash Data-driven organizations … Read more
PyTorch Model Performance Analysis and Optimization — Part 6
How to Identify and Analyze Performance Issues in the Backward Pass with PyTorch Profiler, PyTorch Hooks, and TensorBoard Published in · 8 min read · 4 hours ago Photo by … Read more
7 Visualizations with Python to Handle Multivariate Categorical Data
Conducting the exploratory data analysis (EDA) using data visualization is recommended to help understand the data. Charts such as bar or pie charts are basic choices for plotting simple categorical … Read more
IAM Roles Anywhere credential helper now supports PKCS #11 modules
Today, AWS Identity and Access Management (IAM) Roles Anywhere released credential helper version 1.1.0 to include support for X.509 certificates and private keys that are stored in Public-Key Cryptography Standards … Read more
How To Automatically Import And Combine Multiple Files In R
Stop wasting your time manually importing multiple files Published in · 6 min read · 1 hour ago Photo by ThisisEngineering RAEng on Unsplash In my data scientist job, I … Read more
nimbleHMC version 0.2.0 released, providing improved HMC performance
nimbleHMC provides Hamiltonian Monte Carlo samplers for use with NIMBLE, in particular NUTS samplers. NIMBLE’s HMC samplers can be flexibly assigned to a subset of model parameters, allowing users to … Read more
Balancing Innovation With Safety & Privacy in the Era of Large Language Models (LLM)
As we’ve seen before, it’s a rather trivial task to anonymize the text since we have the beginning and end offsets of each of the entities within the text. However, … Read more
Rugby World Cup explainer using data
Last week, a stereotypical “French” ceremony opened the 10th Rugby World Cup in Stade de France, in the suburbs of Paris, France. As a small boy growing up in the … Read more
Ant Colony Optimization in Action
A working ant. Image created with Dall-E 2 by the author. Member-only story Solving optimization problems and enhancing results with ACO in Python Published in · 10 min read · … Read more
Mastering Data Visualization in R: Plotting Predicted Values with the mtcars Dataset
Data visualization is a powerful tool in a data scientist’s toolkit. It not only helps us understand our data but also presents it in a way that is easy to … Read more
Using React to Build Interactive Interfaces to Exciting Dataset
On the side of my full-time job as the CEO of a small machine-learning company, my hobby is creating beautiful data visualizations. I usually do that using Matplotlib, but I … Read more
How to Build and Manage a Portfolio of Data Assets
Figure 4 above shows what the result could be. There, 12 data domains are presented with about 100 sub-domains. All the organization’s data can be mapped back to the types … Read more
Amazon QuickSight adds new layout and sparkline to KPI visual
Amazon QuickSight introduces a range of exciting enhancements to KPI visual, including templated KPI layouts, support for sparklines, improvements in conditional formatting, and a revamped format pane. The KPI visual … Read more
How Can You Improve Your Forecasting Metrics and Process without Sophisticated Algorithms?
In this section, we will discuss descriptive analytics that use forecasts and historical sales (actuals) in the calculations. Let’s note that all forecasts and actuals are for volumes sold at … Read more
What does it mean when machine learning makes a mistake?
Do our definitions of “mistake” make sense when it comes to ML/AI? If not, why not? Published in · 11 min read · 1 day ago Photo by Kind and … Read more
Prompt Engineering 101: Zero, One, and Few-Shot Prompting
An introduction to a basic prompt engineering strategy Published in · 5 min read · 3 hours ago Image by Alexandra_Koch from Pixabay Introduction Despite their seemingly supernatural capabilities, LLMs … Read more
Is Julia Faster than Python and Numba?
Optimisation Numba is very fast, but is it fast enough? Published in · 16 min read · Just now Photo by Stanos on Unsplash Numba is a widely used optimisation … Read more
A Foundation Model for Medical AI
Introducing PLIP, a foundation model for pathology Published in · 10 min read · 1 hour ago Photo by Tara Winstead: https://www.pexels.com/photo/person-reaching-out-to-a-robot-8386434/ Introduction The ongoing AI revolution is bringing us … Read more
Attract Contributors with ‘help wanted’ Issues
Maintaining a package can be a lonesome activity, which sometimes poses a problem if you prefer team work or if you encounter a very thorny-for-you problem. Beside belonging to a … Read more
Introducing AWS Telecom Services Competency Partners
AWS is excited to introduce the AWS Telecom Services Competency, which provides customers with a vetted list of AWS Partners validated for their expertise and proven success delivering telecom consulting … Read more
Something-of-Thought in LLM Prompting: An Overview of Structured LLM Reasoning
GoT’s novelty lies in its ability to apply transformations to these thoughts, further refining the reasoning process. The cardinal transformations encompass Aggregation, which allows for the fusion of several thoughts … Read more
10 Ways to Improve the Performance of Retrieval Augmented Generation Systems
Tools to go from prototype to production Published in · 9 min read · Just now “Retrieval augmented generation is the process of supplementing a user’s input to a large … Read more
Beyond Grades: Using AI to Forecast and Explain Student Performance
Can we use AI to curb year repetition rates and improve education? Published in · 27 min read · Just now Image by Dids on Pexels Machine Learning (ML) has … Read more