reinforcement Learning rl MAB 강화학습 딥러닝 Thompson sampling Deep Learning LSTM GRU dp TS UCB cnn Multi-armed bandit Multi Armed Bandit Word Embedding value function rnn 알파고 Dynamic Programming Transformer dl Bert attention Attention mechanism 역전파 MDP word2vec 머신러닝 td self-attention 어텐션매커니즘 LeNet ε-greedy Stochastic Bandits epsilon-greedy 톰슨샘플링 GPT-3 AlexNet positional encoding 테이블방법 정책반복 가치반복 벨만방정식 Tabular Method SARSA Contextual Bandit Hierarchical Softmax Negative Sampling Dropout 워드임베딩 XAI SGD on-policy off-policy Back propagation 추천시스템 Q-learning 큐러닝 동적계획법 Machine Learning bellman Monte Carlo luong DQN 몬테카를로 시계열 reward 가치함수 트랜스포머 nlp Recommendation policy Shapley value Shapley ILSVRS very deep CNN VGG-19 VGG-16 루옹 어텐션 메커니즘 Dot product attention Bahdanau Attention Meachanism 바다나우 어텐션 lenet-5 lof local outlier factor 이상치 감지 outlier detection Data Augmentation isolation forest LinUCB Multi-aremd Bandit optimism under the face of uncertainty multi-armed bandits Introduction to multi-armed bandit MAB 개요 introduction to multi armed bandit GPT3 VGG teacher forcing Seq2Seq model 자기부호화기 self-learning auto-encoder 시간차학습 keras 예제 stacked rnn RNN keras RNN tensorflow 코드 gru keras lstm keras double q-learning qlearning value iteration 벨만방정식추정 강화학습개요 최적 정책 optimal policy 최적정책 멀티암드밴딧 Gradient Bandit Gradient Ascent 벌티암드밴딧 입실론그리디 egreedy Reinforcement Leanring Q러닝 순차적의사결정 시계열자료분석 Gated Recurrent Unit forgetgate inputgate Longtermdependency 장기문맥의존성 one-to-many Rumelhart 순차적데이터 BPTT subsamplingfrequentwords Skip-gram CBOW 딥러닝 과적합 over fitting 드롭아웃 Word Embedding 개요 Singular Value Decomposition 특이값분해 이상치 CNN 그래디언트디센트 CNN 역전파 Lecun CNN 역사 기울기강하법요약 Mini-batch 기울기하강법 그래디언트 디센트 기울기 하강법 딥러닝 예제 기울기소실문제 신경망분석 딥러닝 역사 seq2seq Policy Iteration Upper Confidence Bound Temporal Difference AdaDelta adagrad sequence to sequence autoencoder 밴딧 Softmax Convolutional Neural Network EPOCH anomaly detection 과적합 워드투벡 합성곱 relu 뉴럴네트워크 에폭 하강법 텐서플로우 tensorflow keras 차원축소 many-to-many 컨볼루션 퍼셉트론 어텐션 인공신경망 Gradients text mining gradient convolution 베이지안 subsampling 자연어처리 Greedy 기울기 Time difference pca Preference ML 강화 선형대수 역사 아웃라이어 shap Silver Skip Ann lime Adam Ai MC