Bernard Widrow
Bernard Widrow is an American electrical engineer and professor known for his pioneering work in adaptive signal processing and neural networks, particularly as co-inventor of the LMS algorithm and the ADALINE network.
Technology & Innovation
Mixture of depths
Mixture of depths refers to the combination or layering of different depth levels within a medium or context, often used in fields such as image processing, geology, and data visualization to represent or analyze complex structures or scenes.
Certified robustness
Certified robustness refers to formal guarantees that a machine learning model will maintain its performance or output within predefined bounds when subjected to certain types of perturbations or adversarial attacks. It is a key concept in the field of robust machine learning and adversarial defense.
Inception (neural network)
Inception is a deep convolutional neural network architecture designed for image recognition tasks. Introduced by Google researchers in 2014, it uses a novel ‘Inception module’ to improve computational efficiency and accuracy in visual recognition systems.
Hutter Prize
The Hutter Prize is an award aimed at advancing artificial intelligence through compression algorithms, promoting research in machine learning and data processing.
DECA (detailed expression capture and animation)
DECA (detailed expression capture and animation) is a technology and framework used in computer graphics for capturing and animating highly detailed facial expressions. It enables realistic and high-fidelity facial animations by reconstructing 3D facial geometry and expressions from images or video.
Variational diffusion model
A variational diffusion model is a type of generative model that combines principles from variational inference and diffusion processes to generate data through a controlled stochastic process. It is used primarily in machine learning to model complex data distributions by gradually transforming noise into structured data.
Conditional neural process
Conditional neural processes (CNPs) are a class of machine learning models designed to efficiently learn distributions over functions, combining the flexibility of neural networks with the data efficiency of Gaussian processes. They provide a framework for rapid adaptation to new tasks by conditioning on observed data.
UniOcc (unified occupancy prediction)
UniOcc (unified occupancy prediction) is a computational approach designed to estimate and predict occupancy patterns in indoor environments by integrating multiple data sources and using machine learning techniques. It aims to provide accurate, real-time predictions for applications in building management, energy efficiency, and smart environments.
VICReg (variance-invariance-covariance regularization)
VICReg is a regularization technique used in machine learning to ensure the learned representations are both invariant to certain transformations and exhibit specific statistical properties.