Machine learning

machine learning approach where noisy, limited, or imprecise sources are used to provide supervision signal for labeling large amounts of training data in a supervised learning setting

engineering method used when an outcome of interest cannot be easily directly measured, so a model of the outcome is used instead

machine learning for robots

an argument showing that classification is not really possible without some sort of bias

journal

algorithm improvement technique where unnecessary nodes are removed

subfield of machine learning where automatic learning algorithms are applied to metadata about machine learning experiments

method used to normalize the range of independent variables

AIOps (Artificial Intelligence for IT Operations) refers to the use of artificial intelligence, machine learning, and big data analytics to automate and enhance data center management. It helps organizations manage complex IT environments by detecting, diagnosing, and resolving issues more efficiently than traditional methods.

ROCm is an Advanced Micro Devices (AMD) software stack for graphics processing unit (GPU) programming. ROCm spans several domains, including general-purpose computing on graphics processing units (GPGPU), high performance computing (HPC), and heterogeneous computing. It offers several programming models: HIP (GPU-kernel-based programming), OpenMP (directive-based programming), and OpenCL.

an area of supervised machine learning in artificial intelligence. It is closely related to regression and classification, but the goal is to learn from examples a similarity function that measures how similar or related two objects are

form of machine learning where a model learns multiple tasks

in machine learning, function which shows the validation and training score of an estimator for varying numbers of training samples

family of learning algorithms that, instead of performing explicit generalization, compares new problem instances with instances seen in training, which have been stored in memory

Concept in artificial intelligence

mathematical concept

term in machine learning

group of samples that have been tagged with one or more labels

Type of statistical inference

thumb|Architecture of ELMo. It first processes input tokens into embedding vectors by an embedding layer (essentially a lookup table), then applies a pair of forward and backward LSTMs to produce two sequences of hidden vectors, then apply another pair of forward and backward LSTMs, and so on. thumb|How a token is transformed successively over increasing layers of ELMo. At the start, the token is converted to a vector by a linear layer, giving the embedding vector e_0. In the next layer, a forward LSTM produces a hidden vector h_{00}, while a backward LSTM produces another hidden vector h_{00r

Human-in-the-loop (HITL) is used in multiple contexts. It can be defined as a model requiring human interaction. HITL is associated with modeling and simulation (M&S) in the live, virtual, and constructive taxonomy. HITL, along with the related human-on-the-loop are also used in relation to lethal autonomous weapons. Further, HITL is used in the context of machine learning.

Wikimedia list article

non-parametric regression technique

Machine learning algorithm

field associated with machine learning and transfer learning

measure of complexity of real-valued functions

use of machine learning in video games

Google Colab is an online platform hosted by Google to write, run and share code

concept in machine learning where information is used that would not be available when predictions are made

type of regression analysis

Wikimedia glossary list article

posits ability to interpolate within latent manifolds

advanced optimization framework for TensorFlow to enhance computational performance

subfield of machine learning

lossy audio codec developed by Google

artificial intelligence personal assistant device

change of statistical properties over time

journal

field of scientific study

concept in machine learning

Paris-based AI company founded by Charles Kantor

reverse-engineering neural networks

Monte Carlo method for importance sampling and optimization