「
數據應用學院(Data Application Lab)專註於數據, 開辦3年來已向全球知名企業輸送數百Data Scientists,更有不計其數的Data Analysts以及Engineers, Business Analysts。多年的鑽研和專一打造了獨一無二教學方法和求職經驗。一直被模仿, 從未被超越。已被多加北美英文科技媒體列為Top 10 North American Data Bootcamp。學員遍布全球,至今時常還有來自歐洲, 亞太等地的申請者報名。
」
2月24日
《AI人工智慧訓練營》
正式開課!
適合學員背景
理工科或者計算機Computer Science專業, 數學統計專業, 計算機編程愛好者
如果Python背景比較弱, 可以先參加我們的Python基礎入門課程
課程周期
2月24日起,全長6周, 每周六周日2小時課程
課程特色
三大模塊:機器學習, 深度學習與神經網路, 案例項目實踐
雙語教學:機器學習Machine Learning部分全程由英文教學, 方便學員未來求職時對答如流. 深度學習與神經網路和項目實踐部分才用中英雙語
三大名師:Peter(USC Information Institute Post Doc, MachineLearning), Carol (Google工程師, 精通Tensorflow), Eric(Google工程師, AI專家)
前沿技術:課程設計多項AI領域必備前沿技術, 包括全面系統的Machine Learning知識講解梳理, 神經網路與深度學習從入門到實踐,Tensorflow實戰入門, 人臉識別項目, NLP自然語言處理實戰項目
實戰演練:課程內容基於實戰項目, 邊學習邊練習 項目一: Facial Recogniztion 項目二:Natural Language Processing (詳見syllabus)
課程收穫
全面系統了解Machine Learning(Regression, Classification,Dimension Reduction, Clustering)
了解Neutral Network與DeepLearning (Neural Network, deep neutral network, convolution neural network, 調參技巧, RNN等)
用Tensorflow實戰FacialRecognition, 並且嘗試改進與調參
學習和掌握深度學習與NLP自然語言處理 (NLP概念與基礎, word2vec, GloVe, 複雜NLP模型)
用Tensorflow實戰NLP項目
求職助力
課程項目適用於求職簡歷, 增強簡歷效果
加入Data Application Lab海量求職內推網路
簡歷與面試助攻(詳情請諮詢課程老師)
課程內容
Modular 1 – Machine Learning
Class 1 Regression
Basic concept of Regression
Bias-Variance tradeoff
Underfitting vs.Overfitting
Linear regressionanalytical solution
Regularization: Lasso,Ridge,Elastic-Net,Pros and cons of L1and L2 regularization
Advanced techniquesin regression,Gradient Descendent,CoordinatedDescendent,Stochastic GradientDescendent,Random sampleconsensus (RANSAC)
Class 2 Classification
Evaluation Methodsof classification
Basicclassification model: logistic regression, decision tree
ClassificationTypes (how binary and multi-class works)
Ensemble modelmethod: Bagging,Boosting,Stacking
Class 3 DimensionReduction
Dimension reduction overview
Dimension reduction methods:Randomized Projection,Principal Component Analysis,PCA Calculation,Randomized PCA,Sparse PCA
Manifold learning
MultidimensionalScaling:MDS,Isomap
Class 4 Clustering
Unsupervisedlearning introduction
Clustering methods& techniques:K-mean Algorithm,HierarchicalClustering Algorithm,DBSCAN algorithm,Outlierand anomaly detection
Modular 2 – NeuralNetwork & Deep Learning
Class 1
Neuralnetwork basic (which maybe duplicate with NLP part)
Introduction toneural network, include some basic concept like neuron, weights, bias,activation function.
Forward propagation for inference
Training algorithm: backpropagation (use 1hidden layer neural network with binary output as example)
Deep neural network
Fully connectedlayer
Shows how to useDNN for MNIST digit recognition problem
Convolutionalneural network
Motivation: why useCNN in computer vision problem: position invariance.
Convolution
Intro toconvolutional layer + pooling layer
Revisit MNIST problem and show how to use CNNto improve it. #params reduced.
Class 2 Short recap to fully connected layer, convolutional layer and pooling layer.
Introduction tofamous vision problems and corresponding networks
Imageclassification: Alexnet
Object detection:R-CNN
Image segmentation:U-Net
Useful technicalsfor neural network training
Performance: trydifferent network structure, different number of layers and different number ofhidden units in each layer
Converge: sensitive to learning rate
Speed up training:Stochastic Gradient Descent, Momentum
Gradient vanishingproblem: Batch Normalization
Recurrent NeuralNetwork for video learning
RNN basic (thismaybe duplicate with NLP part)
Use example to showhow to use RNN for video analysis.
Reinforcementlearning
Deep Q-learning
Playing Atari gameby DeepMind (Brief introductioninstallation tensorflow)
Class 3 –Tensorflow and Facial Recognition
Brief introductionto Tensorflow: Tensor, operator concept.
Shows one smallnetwork structure and shows how to write it in Tensorflow.
Lab problem:
Face recognition:given face images for 40 person, each have 10 images, use 9 images of eachperson for training. Target is to label the left 40 images (1 per person) tothe right person.
Face recognition iswidely used technologies, such as photo softwares, surveillance.
Class 4
Finish the basic versionfor the Face recognition.
Improve network:
Try differentlearning rate
Add more layer
Add more neuronsfor each layer
Compare DNN and CNN
Try differentoptimizer
Modular 3 – DeepLearning and Natural Language Processing
Class 1
Intro to NLP andDeep Learning
what is NLP?
NLP difficultylevel
Industryapplications
Deep neural networkfor NLP
Phonology andMorphology
Syntax andSemantics
Question Answering
Class 2
Simple Word Vectorrepresentations: word2vec, GloVe
Vector(discrete)Representation
Problem withdiscrete representation
Cooccurence Matrix
Main idea ofword2vec
Main idea of Glove
Class 3
Complicated Modelsfor NLP
Recurrent NeuralNetworks
Alignment
Gated RecurrentUnits
Long-short-term-memories(LSTMs)
Class 4
TensorFlow for NLP
A recap oftensorflow
NLP specifictensorflow
Build a tensorflowbased chatbot from scratch
喜歡這篇文章嗎?立刻分享出去讓更多人知道吧!
本站內容充實豐富,博大精深,小編精選每日熱門資訊,隨時更新,點擊「搶先收到最新資訊」瀏覽吧! 請您繼續閱讀更多來自 大數據應用 的精彩文章: