Technical & Research AI

  • The Chi-squared test for independence is a statistical procedure employed to assess the relationship between two categorical variables – determining whether they are associated or independent. In the dynamic realm of real estate, where a property’s visual appeal often impacts its valuation, the exploration becomes particularly intriguing. But how often do you associate a house’s […]
  • On March 5, 8am PT, learn how NVIDIA Metropolis microservices for Jetson Orin helps you modernize your app stack, streamline development and deployment, and future-proof your apps with the ability to bring the latest generative AI capabilities to any customer through simple API calls. Source
  • Optimising multi-model collaboration with graph-based orchestrationOrchestra — photographer Arindam Mahanta by unsplashIntegrating the capabilities of various AI models unlocks a symphony of potential, from automating complex tasks that require multiple abilities like vision, speech, writing, and synthesis to enhancing decision-making processes. Yet, orchestrating these collaborations presents a significant challenge in managing the inner relations and dependencies. Traditional linear […]
  • Let’s look together under the hood with Python and PyTorchContinue reading on Towards Data Science »
  • Connecting the dots for a theoretical analysis of Graph Neural Network modelsContinue reading on Towards Data Science »
  • Converting a Colab notebook to two microservices with support for Milvus and NeMo GuardrailsContinue reading on Towards Data Science »
  • NVIDIA is collaborating as a launch partner with Google in delivering Gemma, a newly optimized family of open models built from the same research and technology used to create the Gemini models. An optimized release with TensorRT-LLM gives users the ability to develop with LLMs using only a desktop with an NVIDIA RTX GPU. Created […]
  • This article will show you different approaches you can take to create embeddings for your dataContinue reading on Towards Data Science »
  • Consistently beautiful plots with less code and minimal effortContinue reading on Towards Data Science »
  • Utilize large model inference containers powered by DJL Serving & Nvidia TensorRTContinue reading on Towards Data Science »
  • Applying chat templates to generative LM evaluation testsPhoto by Google DeepMind on Unsplash“Building solid evals should be the starting point for any LLM-based system or product (as well as conventional machine learning systems).” — Eugene Yan, linktl;drChat models are typically fine-tuned on datasets formatted with a prompt template. These chat templates are programmed recipes that convert a chat conversation […]
  • Join us at the Game Developers Conference March 18-22 to discover how the latest generative AI and NVIDIA RTX technologies are accelerating game development. Source
  • Motivation, definition, and applicationsContinue reading on Towards Data Science »
  • Modeling parameters by highest likelihood of observing dataContinue reading on Towards Data Science »
  • Visualizing Satellite Images Captured over Volcanos and Wildfires in Various Spectral BandsContinue reading on Towards Data Science »
  • Use your favorite models in combination with meta-learners to make valid causal statementsContinue reading on Towards Data Science »
  • The ultimate self-study guide for all levelsImage by authorWhile everyone focuses on AI and predictive inference, standing out requires mastering not just prediction, but understanding the “why” behind the data — in other words, mastering causal inference.You have heard that “correlation does not imply causation”, but few truly grasp its implications or know when to confidently assert causality.The distinction […]
  • Source
  • Shows our study based on the WSDM 2023 Toloka VQA ChallengeImage generated by GPT-4VA year has passed since the Toloka Visual Question Answering (VQA) Challenge at the WSDM Cup 2023, and as we predicted back then, the winning machine-learning solution didn’t match up to the human baseline. However, this past year has been packed with breakthroughs […]
  • How to solve binary classification problems using Bayesian methods in Python.Bayesian Thinking — OpenAI DALL-E Generated Image by AuthorIntroductionIn this article, I will build a simple Bayesian logistic regression model using Pyro, a Python probabilistic programming package. This article will cover EDA, feature engineering, model build and evaluation. The focus is to provide a simple framework for Bayesian logistic […]

The following permanent links are provided because of the high submission rate of preprint and postprint manuscripts on the topics of Artificial Intelligence and Machine Learning. Be prepared to go down the rabbit hole!