Model predictive control with neural dynamics
Model predictive control with neural dynamics integrates neural network models into the framework of model predictive control for enhanced decision-making in dynamic systems.
Joaquimma Anna
Ray Kurzweil
Ray Kurzweil is an American inventor, futurist, and author known for his work in artificial intelligence and his predictions about technological advancements.
WebQuestions
WebQuestions is a dataset for evaluating question answering systems, focusing on open-domain questions and their corresponding answers from Wikipedia.
FastText
FastText is an open-source library for efficient text representation and classification, developed by Facebook’s AI Research lab.
Never give up (exploration bonus)
The ‘Never give up’ exploration bonus encourages perseverance in challenging tasks and goals, emphasizing the importance of resilience in various contexts.
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.
OpenUnmix (source separation)
OpenUnmix is an open-source tool for music source separation designed to isolate individual audio components such as vocals and instruments from mixed audio tracks. It employs deep learning techniques to perform this task, making it a notable contribution to audio signal processing and music information retrieval.
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.