2017 신입 교육 일정 (기계학습 관련)

첫째 주


6/12(할당 첫날)


비즈니스 소개


등록github


기계 학습

  • AI, ML 및 DL 관계
  • 주파수 통계 vs. 베일스 통계
  • 최대 유사 추정 vs. 베일스 추정
  • 과도한 학습
  • 대책: 정규화,dropout
  • 매개변수 조정
  • train-validation-test-split
  • 교사는 패턴이 있다
  • 분류 모델
  • NN (Neural Network)
  • gradient descent
  • back propagation
  • SVM (Support Vector Machine)
  • 모를 수도 있다:kernel trick
  • DT (Decision Tree)
  • 모를 수도 있다: informational gain
  • RF (Random Forest)
  • 참조: bootstrap resampling
  • Python

  • jupyter notebook의 소개
  • test.ipynb
    %matplotlib inline
    import matplotlib.pyplot as plt
    import numpy as np
    
    x = np.arange(0,10,0.1)
    y = np.sin(x)
    plt.plot(x,y)
    

    6/13


    scikit-learn

  • sklearn 작업 흐름
  • model = Model()
  • model.fit()
  • model.predict()
  • 6/14


    tensorflow

  • tensorflow 작업 흐름
  • w/anaconda@windows10
  • 설치

    Deep Neural Network

  • DNN의 기본 말
  • activations
  • tanh
  • relu
  • lrelu
  • prelu
  • elu
  • optimizer
  • sgd
  • momentum
  • adagrad/adadelta/rmsprop
  • adam
  • initializer
  • xavier init.
  • he init.
  • 6/15


    keras

  • keras 워크플로우
  • Autoencoder

  • denoising AE
  • sparse AE
  • variational AE(나중에 설명
  • Anomaly Detection


    6/16


    Convolutional Neural Network

  • convolution
  • pooling
  • Transfer Learning


    Normalization

  • batch normalization
  • weight normalization
  • layer normalizaiton
  • Image Recognition

  • LeNet
  • AlexNet
  • ZFNet
  • VGGNet
  • NIN
  • GoogLeNet
  • ResNet
  • 둘째 주


    6/19


    Keras

  • Practice: CNN
  • 6/20


    Keras

  • Practice: Transfer Learning
  • 6/21


    Keras

  • Practice: Transfer Learning
  • Model Compression

  • Deep Compression
  • Depse-wise Conv.
  • Xception
  • Mobilenet
  • 6/22


    Keras

  • Practice: Transfer Learning
  • Similarity Learning

  • Siamese Network
  • 6/23


    Object Detection

  • R-CNN
  • SPPNet
  • Fast R-CNN
  • Faster R-CNN
  • Overfeat
  • AttentionNet
  • SSD
  • YOLO
  • 셋째 주


    6/26


    Semantic Segmentation

  • Deconvolution
  • FCN
  • Mask R-CNN
  • Recurrent Neural Networks

  • LSTM
  • GRU
  • Bi-RNN
  • Neural Machine Translation

  • Seq2Seq
  • Attention
  • Slicenet
  • Image Caption Generation


    Keras

  • Practice: RNN-LSTM
  • 6/27


    Natural Language Processing

  • word2vec
  • Skipgram
  • CBoW(Continuous Bag of Words)
  • Glove
  • sentence2vec
  • BoW
  • Recursive Neural Network
  • Glove
  • 6/28


    Generative Models

  • GAN: Generative Adversarial Networks
  • DCGAN
  • Conditional GAN
  • Pix2Pix
  • Adversarial Examples


    6/29


    Generative Models

  • VAE: Variational Autoencoder
  • DRAW
  • Pixel RNN/Pixel CNN
  • Wavenet
  • Bytenet
  • 6/30


    Understanding CNN

  • Maximally Activating Patches
  • Occlusion Maps
  • Saliency Maps
  • Features Inversion via backprop
  • Neural Style Transfer

  • Deep Dream
  • Neural Art
  • 7/3


    Reinforcement Learning

  • MDP
  • Policy Gradient
  • AlphaGo
  • 7/12 이후


    Reinforcement Learning

  • Q-Learning
  • DQN
  • Actor-Critic
  • A3C
  • NN w/ External Memory

  • Neural Turing Machine
  • Differential Neural Computer
  • Meta Learning

  • Evolutional Strategy
  • One-Shot Learning

  • Matching Networks
  • Semi-Supervised Learning

  • GAN/VAE/Virtual Adversarial Training
  • Self-Driving Cars

  • NVIDIA Model
  • Localization
  • Sensor Fusion
  • Kalman filter
  • PID Control
  • SLAM
  • Path Planning
  • Robotics

  • Perception/Decision/Action
  • 좋은 웹페이지 즐겨찾기