
NoGAN: New Generation of Synthetic Data (Video)
- Vincent Granville
- September 28, 2023
My talk at the Generative AI Conference, London, September 2023. View or download the PowerPoint presentation, here. I introduce a new, NoGAN alternative to standard tabular data synthetization. It is designed to run faster by several orders of magnitude, compared to training generative adversarial networks (GAN). In addition, the quality of the generated data is […]
Read More
GenAI: Fast Data Synthetization with Distribution-free Hierarchical Bayesian Models
- Vincent Granville
- September 22, 2023
Deep learning models such as generative adversarial networks (GAN) require a lot of computing power, and are thus expensive. Also, they may not convergence. What if you could produce better data synthetizations, in a fraction of the time, with explainable AI and substantial cost savings? This is what Hierarchical Deep Resampling was designed for. It […]
Read More
New Python Library to Evaluate AI-generated Data and Compare Models
- Vincent Granville
- September 19, 2023
Called GenAI-Evalution, you use it for instance to assess the quality of tabular synthetic data. In this case, it measures how faithfully the synthetization mimics the real data it is derived from, by comparing the full joint empirical distributions (ECDF) attached to the two datasets. It works both with categorical and numerical features, and returns […]
Read More
Generative AI Technology Break-through: Spectacular Performance of New Synthesizer
- Vincent Granville
- August 2, 2023
Neural network methods have overshadowed all other techniques in the last decade, to the point that alternatives are simply ignored. And for good reasons: techniques such as generative adversarial networks (GAN) proved very successful in some contexts, especially computer vision. Indeed, there has been several attempts to turn every problem and traditional method — regression, […]
Read More
Synthesizing Geospatial Data with A Simple NoGAN Technique
- Vincent Granville
- July 28, 2023
If you regularly read my articles, you know that I developed several different techniques for data synthetization. Many are explained in details in my upcoming book Synthetic Data and Generative AI (Elsevier), available here. It includes generative adversarial networks (GANs), copulas, agent-based modeling, methods based on interpolation, correlated noise mixtures, and more. The technique presented […]
Read More
High-value AI and Machine Learning Certifications Under $50
- Vincent Granville
- May 21, 2023
Our AI/ML research lab now offers a quick path to certification in generative AI and other modern topics relevant to new developments in the industry, as well as traditional and specialized certifications and training. All in Python. Probably the fastest and most affordable way to earn professional, high value credentials offered by one of the […]
Read More
Autonomous Driving: Boosting Optical Flow with Synthetic Data
- Michael Galarnyk
- April 27, 2023
- computer vision
- optical flow
- synthetic data
Optical flow is defined as the task of estimating per-pixel motion between video frames. Optical flow models take two sequential frames as input and return as output a flow vector that predicts where each pixel in the first frame will be in the second frame. Optical flow is an important task for autonomous driving, but […]
Read More
Massively Speed-Up your Learning Algorithm, with Stochastic Thinning
- Vincent Granville
- April 7, 2023
Dramatically Speed-Up your Learning Algorithm, with Stochastic Thinning. Includes use case, Python code, regression and neural network illustrations.
Read More
Data Synthetization: enhanced GANs vs Copulas
- Vincent Granville
- March 8, 2023
Using case studies, I compare generative adversarial networks (GANs) with copulas to synthesize tabular data. I discuss back-end and front-end improvements to help GANs better replicate the correlation structure present in the real data. Likewise, I discuss methods to further improve copulas, including transforms, the use of separate copulas for each population segment, and parametric […]
Read More
Data Synthetization Explained in One Picture
- Vincent Granville
- February 23, 2023
The diagram is organized as follows. Dashed blue lines are associated to GANs (generative adversarial networks), where the goal is to produce a sequence of synthetic datasets that get better and better at mimicking the structure present in the real data, over successive iterations. The diagram features 5 such iterations, with the synthetized datasets denoted […]
Read More
You must be logged in to post a comment.