정보관리기술사 & 컴퓨터시스템응용기술사 : Vol.09 인공지능 (개정증보1판)

권대호,권영식

저자:권영식
성균관대학교정보보호학과졸업(공학석사).삼성종합기술원연구원,삼성전자선임/책임/수석연구원,국립공원공단정보융합실장,컴퓨터시스템응용기술사,정보시스템수석감리원,정보통신특급감리원,정보통신특급기술자,과학기술정보통신부IT멘토,데이터관리인증심사원(DQC-M),韓(한)·日(일)기술사교류회위원.http://cafe.naver.com/96starpe운영자.

저자:권대호
연세대학교전기전자공학부
중앙대학교소프트웨어학부컴퓨터공학사

PART1.인공지능(人工知能,ArtificialIntelligence)의개요
1.인공지능(ArtificialIntelligence)의역사
2.인공지능
3.인공지능(AI)의특이점(Singularity)
4.아실로마(ASILOMA)AI(인공지능)원칙
5.규칙기반모델
6.추천엔진(RecommendationEngine)
7.전문가시스템(ExpertSystem)
8.정규표현식과유한오토마타
9.유한오토마타(FiniteAutomata)
10.튜링테스트(TuringTest)
11.에이전트(Agent)-1교시형답안
12.에이전트(Agent)-2교시형답안
13.킬스위치(KillSwitch)
14.트롤리딜레마(TrolleyDilemma)
15.인공지능(AI)윤리의개념,주요사례,고려사항및추진방향
16.이용자중심의지능정보사회를위한원칙
17.약인공지능(WeakAI),강인공지능(StrongAI),초인공지능(SuperAI),AI학습데이터품질

PART2.인공지능알고리즘(Algorithm)
18.유전자알고리즘(GeneticAlgorithm)
19.그리디알고리즘(GreedyAlgorithm)
20.상관분석(CorrelationAnalysis)
21.Data분석에서상관관계(Correlation)와인과관계(Causation)의비교설명
22.회귀분석(RegressionAnalysis)
23.로지스틱회귀분석(LogisticRegressionAnalysis)
24.Cluster(클러스터)분석-1교시형답안
25.군집분석(ClusterAnalysis)-2교시형답안
26.계층적군집분석(HierarchicalClustering)
27.자카드(Jaccard)계수
28.해밍거리(HammingDistance)
29.해밍코드(HammingCode)의오류검색과수정방법,그리고활용사례에대해서설명하시오.(Data는4Bit(1101)로가정하고짝수패리티(EvenParity)를사용한다)
30.유클리디안거리(EuclideanDistance)
31.유클리디안거리(EuclideanDistance)계산하시오.(A,B)(A,C)간의거리
32.마할라노비스거리(MahalanobisDistance)계산하시오.(A,B)(A,C)간의거리
33.코사인유사도(CosineSimilarity)
34.협업필터링(CollaborativeFiltering)
35.추천시스템(RecommenderSystem)
36.Apriori(연관규칙)알고리즘
37.지지도(Support),신뢰도(Confidence),향상도(Lift)
38.사례1(TV구입시DVD구입),사례2(우유구입시주스구입)에대해연관규칙(지지도,신뢰도,향상도)을제시하시오.
39.앙상블학습(EnsembleLearning)
40.머신러닝(MachineLearning)에활용,앙상블(Ensemble)기법
41.Bagging과Boosting비교
42.랜덤포레스트(RandomForest)
43.의사결정트리(DecisionTree)
44.K-NN(K-NearestNeighbor)
45.시계열분석
46.시계열분석(ARIMA)
47.SVM(SupportVectorMachine)-1교시형답안
48.SVM(SupportVectorMachine)-2교시형답안
49.베이즈(Bayes)정리
50.크기와모양이같은공이상자A에는검은공2개와흰공2개,상자B에는검은공1개와흰공2개가들어있다.두상자A,B중임의로선택한하나의상자에서공을1개꺼냈더니검은공이나왔을때,그상자에남은공이모두흰공일확률은?(베이즈(Bayes)정리를활용하시오)
51.K-Means
52.DBSCAN(DensityBasedSpatialClusteringwithApplicationNotes)
53.차원축소(DimensionalityReduction)
54.오토인코더(AutoEncoder)
55.군집분석기법인SOM(SelfOrganizationMap)에대하여설명하시오.
가.SOM정의및특징
나.SOM구성요소
다.SOM과신경망분석기법차이
56.특징추출(FeatureExtraction)
57.주성분분석,PCA(PrincipalComponentAnalysis)
58.독립성분분석,ICA(IndependentComponentAnalysis)
59.마르코프결정프로세스(MarkovDecisionProcess,MDP)
60.은닉마르코프모델(HMM-HiddenMarkovModel)
61.몬테카를로트리탐색(MCTS)
62.몬테카를로방법(MonteCarloMethod)
63.Q-Learning
64.Tokenization(토근화),N-gram
65.Word2Vec
66.워드임베딩(WordEmbedding)
67.Word2Vec학습모델,CBOW(ContinuousBagOfWords),Skip-gram
68.인공신경망의오류역전파(Backpropagation)알고리즘
69.평균제곱오차(MSE,MeanSquareError)
70.오차검증(ErrorValidation)
71.텐서(Tensor)
72.선택편향(SelectionBios)
73.공분산(Covariance)
74.편상관분석(PartialCorrelationAnalysis)
75.최소제곱법(OrdinaryLeastSquares)
76.부트스트랩(Bootstrap)
77.모수검증과비모수검증

PART3.심층신경망상세
78.일반적인프로그램방식과MachineLearning(기계학습)프로그래밍방식
79.귀납적(Inductive)/연역적(Deductive)사고
80.귀납적사고(InductiveReasoning)와기계학습(MachineLearning)
81.기계학습(MachineLearning)모델링과모델옵스(ModelOps)에대해설명하시오.
82.AI(ArtificialIntelligence),ML(MachineLearning),DL(DeepLearning)관계와차이점
83.ML(MachineLearning)과DL(DeepLearning)차이
84.기계학습(MachineLearning)
85.지도학습(SupervisedLearning)
86.비지도(비감독)(UnsupervisedLearning)학습
87.강화학습(ReinforcementLearning)
88.딥러닝(DeepLearning)
89.MCP(McCulloch-Pitts)뉴런(Neuron)과Perceptron이론
90.뉴로모픽칩(NeuromorphicChip)
91.헵규칙(HebbRule)
92.퍼셉트론(Perceptron)
93.아달라인(Adaline-AdaptiveLinearNeutron)
94.활성화함수(ActivationFunction)-1
95.활성화함수(ActivationFunction)-2
96.신경망학습-FFNN(FeedForwardNeuralNetwork)
97.딥러닝(DeepLearning)의파라미터(Parameter)와하이퍼파라미터(Hyperparameter)를비교하고하이퍼파라미터의튜닝방법을설명하시오.
98.역전파법(Back-Propagation)
99.기울기소실문제(VanishingGradientProblem)
100.경사하강법(GradientDescent)
101.과적합(Overfitting)과부적합(Underfitting),적합(Bestfitting)
102.과적합(Overfitting)과부적합(Underfitting)해결방안
103.과적합(Overfitting)의발생이유와해결방안
104.Overfitting과Underfitting의문제점과대응방안
105.Dropout
106.ANN(ArtificialNeuralNetwork)
107.DNN(DeepNeuralNetwork)
108.CNN(ConvolutionNeuralNetwork)
109.R-CNN(Region-basedCNN)
110.YOLO(youOnlyLookOnce)
111.RNN(RecurrentNeuralNetwork)
112.LSTM(LongShort-TermMemory)
113.GRU(GatedRecurrentUnit)
114.RBM(RestrictedBoltzmannMachine)
115.DBN(DeepBeliefNetwork)
116.DQN(DeepQ-Network)
117.GAN(GenerativeAdversarialNetworks)
118.딥페이크(Deepfake)
119.DL4J(DeepLearning4J)
120.신경망처리장치(NPU:NeuralProcessingUnit)
121.혼동행렬(ConfusionMatrix)
122.MachineLearning(기계학습)의평가방법-Accuracy(정확도),Recall(재현율),Precision(정밀도)
123.F1Score
124.다음예시에서정확도(Accuracy),정밀도(Precision),재현율(Recall),F1Score를각각구하시오.(음치와정상의예측비율)

PART4.인공지능활용
125.음성인식기술,ASR(AutomaticSpeechRecognition),NLU(NaturalLanguageUnderstanding),TTS(TexttoSpeech)
126.음성인식(VoiceRecognition)
127.챗봇(ChatBot)
128.가상개인비서(VirtualPersonalAssistant)
129.패턴인식(PatternRecognition)
130.머신러닝파이프라인(MachineLearningPipeline)
131.자연어처리(NaturalLanguageProcessing)-1
132.자연어처리(NaturalLanguageProcessing)-2
133.엑소브레인(Exobrain)
134.엑소브레인(Exobrai