Transfer learning
This topic is related to the psychological literature on transfer of learning, although practical ties between the two fields are limited.[2] Since transfer learning makes use of training with multiple objective functions it is related to cost-sensitive machine learning and multi-objective optimization.[3] In 1976, Bozinovski and Fulgosi published a paper addressing transfer learning in neural network training.[4][5] The paper gives a mathematical and geometrical model of the topic.In 1981, a report considered the application of transfer learning to a dataset of images representing letters of computer terminals, experimentally demonstrating positive and negative transfer learning.[6] In 1992, Lorien Pratt formulated the discriminability-based transfer (DBT) algorithm.[7] By 1998, the field had advanced to include multi-task learning,[8] along with more formal theoretical foundations.In the 2020 paper, "Rethinking Pre-Training and self-training",[15] Zoph et al. reported that pre-training can hurt accuracy, and advocate self-training instead.The definition of transfer learning is given in terms of domains and tasks., a task consists of two components: a label space, is learned from the training data consisting of pairs[18] Transfer learning has been applied to cancer subtype discovery,[19] building utilization,[20][21] general game playing,[22] text classification,[23][24] digit recognition,[25] medical imaging and spam filtering.[26] In 2020, it was discovered that, due to their similar physical natures, transfer learning is possible between electromyographic (EMG) signals from the muscles and classifying the behaviors of electroencephalographic (EEG) brainwaves, from the gesture recognition domain to the mental state recognition domain.It was noted that this relationship worked in both directions, showing that electroencephalographic can likewise be used to classify EMG.[27] The experiments noted that the accuracy of neural networks and convolutional neural networks were improved[28] through transfer learning both prior to any learning (compared to standard random weight distribution) and at the end of the learning process (asymptote).Moreover, the end-user of a pre-trained model can change the structure of fully-connected layers to improve performance.[29] Several compilations of transfer learning and domain adaptation algorithms have been implemented: This artificial intelligence-related article is a stub.
Machine learningdata miningSupervised learningUnsupervised learningSemi-supervised learningSelf-supervised learningReinforcement learningMeta-learningOnline learningBatch learningCurriculum learningRule-based learningNeuro-symbolic AINeuromorphic engineeringQuantum machine learningClassificationGenerative modelingRegressionClusteringDimensionality reductionDensity estimationAnomaly detectionData cleaningAutoMLAssociation rulesSemantic analysisStructured predictionFeature engineeringFeature learningLearning to rankGrammar inductionOntology learningMultimodal learningApprenticeship learningDecision treesEnsemblesBaggingBoostingRandom forestLinear regressionNaive BayesArtificial neural networksLogistic regressionPerceptronRelevance vector machine (RVM)Support vector machine (SVM)Hierarchicalk-meansExpectation–maximization (EM)DBSCANOPTICSMean shiftFactor analysisGraphical modelsBayes netConditional random fieldHidden MarkovRANSACLocal outlier factorIsolation forestArtificial neural networkAutoencoderDeep learningFeedforward neural networkRecurrent neural networkreservoir computingBoltzmann machineRestrictedDiffusion modelConvolutional neural networkAlexNetDeepDreamNeural radiance fieldTransformerVisionSpiking neural networkMemtransistorElectrochemical RAMQ-learningTemporal difference (TD)Multi-agentSelf-playActive learningCrowdsourcingHuman-in-the-loopCoefficient of determinationConfusion matrixLearning curveROC curveKernel machinesBias–variance tradeoffComputational learning theoryEmpirical risk minimizationOccam learningPAC learningStatistical learningVC theoryTopological deep learningECML PKDDNeurIPSGlossary of artificial intelligenceList of datasets for machine-learning researchList of datasets in computer vision and image processingOutline of machine learningimage classificationtransfer of learningcost-sensitive machine learningmulti-objective optimizationneural networkLorien Prattmulti-task learningfeature spacemarginal probability distributionMarkov logic networksBayesian networksbuilding utilizationgeneral game playingtext classificationspam filteringelectromyographicelectroencephalographicgesture recognitionneural networksconvolutional neural networksdomain adaptationCrossover (genetic algorithm)