WebQuestions
WebQuestions is a dataset for evaluating question answering systems, focusing on open-domain questions and their corresponding answers from Wikipedia.
Technology & Innovation
FastText
FastText is an open-source library for efficient text representation and classification, developed by Facebook’s AI Research lab.
Sim-to-real transfer for RL
Sim-to-real transfer for reinforcement learning (RL) involves adapting models trained in simulation to perform in real-world environments, addressing challenges like domain gaps.
Apprenticeship learning
Apprenticeship learning is a method in machine learning where an agent learns to perform tasks by observing expert demonstrations. It is closely related to imitation learning and is used to teach autonomous systems by mimicking expert behavior rather than relying solely on trial-and-error.
Laplace approximation for neural networks
The Laplace approximation for neural networks is a Bayesian technique that approximates the posterior distribution of network parameters using a Gaussian centered at the maximum a posteriori estimate. It provides a computationally efficient way to quantify uncertainty in neural network predictions.
HMDB51 (human motion database)
HMDB51 is a comprehensive database designed for human motion analysis, containing videos of various human activities categorized for research purposes.
Graph isomorphism network (GIN)
Graph isomorphism network (GIN) is a type of graph neural network designed to effectively capture graph structures by mimicking the Weisfeiler-Lehman graph isomorphism test, enabling powerful graph representation learning.
Structural similarity index (SSIM)
The Structural Similarity Index (SSIM) is a perceptual metric used to measure the similarity between two images. It assesses image quality degradation caused by processing such as compression or transmission errors by comparing luminance, contrast, and structural information.
Eliezer Yudkowsky
Eliezer Yudkowsky is a researcher and writer known for his work on artificial intelligence and rationality. He is a co-founder of the Machine Intelligence Research Institute.
Graph neural network
A graph neural network (GNN) is a type of deep learning model designed to process data structured as graphs. It leverages the relationships and interactions between nodes and edges to perform tasks such as node classification, link prediction, and graph classification.