Andrew Y. Ng
(16 articles)
Motor Learning
Process by which robots or AI systems acquire, refine, and optimize motor skills through experience and practice.
Generality: 675
Segmentation
Process in AI that subdivides an image or dataset into multiple parts to simplify and/or change the perspective of comprehension.
Generality: 831
Anomaly Detection
Process of identifying unusual patterns that deviate from expected behavior, often used to detect fraud, network intrusions, or unusual transactions.
Generality: 860
Best-of-N
A strategy in AI that involves generating multiple outputs and selecting the best one based on a predefined criterion or scoring function.
Generality: 575
Inductive Bias
Assumptions integrated into a learning algorithm to enable it to generalize from specific instances to broader patterns or concepts.
Generality: 827
Discount Factor
Multiplicative factor used to reduce future values or rewards to their present value in decision-making processes, particularly in reinforcement learning.
Generality: 790
Neuromorphic Chips
Specialized hardware designed to mimic the neural structures and functioning of the human brain to enhance computational efficiency and speed in processing AI algorithms.
Generality: 650
Autonomous Learning
Systems capable of learning and adapting their strategies or knowledge without human intervention, based on their interactions with the environment.
Generality: 870
MTL
Multi-Task Learning
Multi-Task Learning
ML approach where a single model is trained simultaneously on multiple related tasks, leveraging commonalities and differences across tasks to improve generalization.
Generality: 761
Transfer Capability
A feature of AI systems that allows acquired knowledge in one domain or task to be applied to another distinct but related domain or task.
Generality: 775
IRL
Inverse Reinforcement Learning
Inverse Reinforcement Learning
Technique in which an algorithm learns the underlying reward function of an environment based on observed behavior from an agent, essentially inferring the goals an agent is trying to achieve.
Generality: 658
LDA
Latent Dirichlet Allocation
Latent Dirichlet Allocation
Generative statistical model often used in natural language processing to discover hidden (or latent) topics within a collection of documents.
Generality: 794
Semi-Supervised Learning
ML approach that uses a combination of a small amount of labeled data and a large amount of unlabeled data for training models.
Generality: 800
Imitation Learning
AI technique where models learn to perform tasks by mimicking human behavior or strategies demonstrated in training data.
Generality: 850
TPU
Tensor Processing Units
Tensor Processing Units
Specialized hardware accelerators designed to significantly speed up the calculations required for ML tasks.
Generality: 821
Instruction-Following
Ability to accurately understand and execute tasks based on given directives.
Generality: 725