Image Classification with PyTorch and SHAP: Can you Trust an Automated Car?

Build an image classification model with PyTorch. We compare it to a benchmark using intensity thresholds, evaluate it and interpret it using SHAP.

Your Vision-Language Model Might Be a Bag of Words

Multimodal AI is the talk of the town. With the recent release of GPT-4, we are seeing myriads of new possible applications and future technologies that were unthinkable six months ago.

What is Parametric and Non-Parametric in Statistic? Learn with Python Example

While learning Data Science, I am sure you will encounter many unfamiliar terms. Most of the statistical word that exists in the book or online courses would mention the word with little proper…

2 Simple Steps To Reduce the Memory Usage of Your Pandas Dataframe

Reduce the required memory of a pandas dataframe of a large dataset to fit into your RAM

This AI newsletter is all you need #39

The last week in AI was dominated by the sudden release of GPT-4 by OpenAI. We note 4 key areas of improvement of GPT-4 over GPT-3.5;

Automated Python Application Testing Using GitHub Actions

Testing your application is a crucial step in any software development or data science workflow. Testing allows you to ensure that the code functions as expected, reduces the likelihood of bugs or…

The Hierarchy of ML tooling on the Public Cloud

Not all ML services are built the same. As a consultant working in the public cloud, I can tell you that you are spoilt for options for AI / ML tooling on the 3 big public clouds, Azure, AWS, and GCP.

Comparing List Comprehensions vs. Built-In Functions in Python: Which Is Better?

Comparing List Comprehensions vs. Built-In Functions in Python: Which Is Better?. An in-depth analysis of syntax, readability, and performance.

Finding Spelling Bee Pangrams with GPT-4 and SpaCy

Solving the New York Times Spelling Bee can be a rewarding experience that balances a challenge with the pleasure of word exploration. While it’s not always a walk in the park, the satisfaction…

What is a Solution Architect at NVIDIA?

Adam did a Ph.D. in information retrieval systems way before AI was cool in 2008 (finished in 2013). He has lots of experience in scaling models and deploying all the components online. Adam is also…