ApolloScape (baidu autonomous driving)
ApolloScape is Baidu’s autonomous driving project focusing on the development of self-driving technologies and data collection.
Artificial Intelligence
Motion planning with neural networks
Motion planning with neural networks involves using artificial neural networks to compute feasible paths for autonomous agents or robots within an environment. This approach leverages machine learning techniques to improve the efficiency and adaptability of traditional motion planning algorithms.
Self-driving car
A self-driving car is a vehicle capable of sensing its environment and operating without human input. Utilizing a combination of sensors, cameras, radar, and artificial intelligence, these vehicles aim to improve road safety and transportation efficiency.
Backpropagation
Backpropagation is a fundamental algorithm used in training artificial neural networks by efficiently computing gradients needed for optimization. It enables the adjustment of network weights through the chain rule of calculus, facilitating learning in multi-layer networks.
RoseTTAFold
RoseTTAFold is a deep learning-based computational method developed for predicting protein structures from amino acid sequences. It integrates multiple neural network architectures to generate accurate three-dimensional protein models, aiding biological research and drug discovery.
AI for protein design
AI for protein design involves the use of artificial intelligence techniques to create novel proteins with specific structures and functions. This field integrates computational methods, machine learning, and biological knowledge to accelerate and enhance the protein engineering process.
Preprocessing bias mitigation
Preprocessing bias mitigation involves techniques used to reduce bias in datasets before they are used for machine learning. These methods aim to enhance fairness and accuracy in AI systems.
SimSiam (simple siamese network)
SimSiam is a self-supervised learning framework that employs Siamese networks to facilitate feature extraction without negative samples.
Neural Turing machine
A Neural Turing Machine (NTM) merges neural networks with external memory resources, enabling the model to learn and store information dynamically.
Variational information maximizing exploration (VIME)
Variational Information Maximizing Exploration (VIME) is a reinforcement learning technique designed to improve exploration by encouraging agents to seek out novel states through information gain. It leverages variational inference to estimate the agent’s uncertainty about the environment dynamics, thus guiding exploration in high-dimensional or complex tasks.