最新最前沿的AI人工智慧訓練營 了解一下

「

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

Class 2 Classification

Class 3 DimensionReduction

Class 4 Clustering

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！