˙人工智慧在資安攻防的角色
˙人工智慧被駭客利用攻擊的方法
˙人工智慧帶給資安防護的契機
˙人工智慧資安技術研發展望

◆Getting Started with Data Analytics in Python

˙Anaconda Python
˙Python package installing with setuptools
˙IPython shell and IPython notebook
˙Help and references

◆Part 1 : Fundamental data analytics in Python- Numpy

˙Numpy Array
˙EigenValue and EigenVector using Numpy
˙Random Number
˙One-dimentional slicing and indexing
˙Array shape
˙Stacking arrays
˙Splitting NumPy arrays
˙Numpy array attributes
˙Linear algebra with NumPy
˙Disregarding negative and extreme values
˙[Lab1] Small case practices in log data

◆Part 2: Fundamental data analytics in Python- Pandas

˙Data Frame and Series data structure
˙Querying data in pandas
˙Statistics with pandas DataFrame
˙Data aggregation
˙Concatenating, joining, and appending DataFrames
˙Handling missing values
˙Dealing with dates
˙Pivot tables
˙[Lab 2] Statistic analysis cloud audit log via Pandas

◆Part 3: Advanced Data analytics using sklearn library

˙Supervised learning
˙Unsupervised learning
˙Cross Validation
˙Model Complexity and GridSearch
˙Performance metrics
˙In depth- support vector machine
˙In depth- trees and forest
˙[Lab 3] Malware classification

◆Part 4: TensorFlow 123

˙Quick understanding the types of deep learning
˙TensorFlow installation
˙Basic Models (linear regression, logistic regression, nearest neighbor)
˙Neural network (autoencoder, bidirectional rnn, convolutional network, multilayer perceptron, recurrent network)
˙How to analyze neural network
˙[Lab] Malware analysis using Deep Learning

◆Traceability and Monitoring

˙Traceability
˙Relationships and Dependencies
˙Approving Requirements
˙Baselining Approved Requirements
˙Monitoring Requirements Using a Traceability Matrix
˙The Requirements Life Cycle
˙Managing Changes to Requirements

◆Solution Evaluation

˙Purpose of Solution Evaluation
˙Recommended Mindset for Evaluation
˙Plan for Evaluation of the Solution
˙Determine What to Evaluate
˙When and How to Validate Solution Results
˙Evaluate Acceptance Criteria and Address Defects
˙Facilitate the Go/No-Go Decision
˙Obtain Signoff of the Solution
˙Evaluate the Long-Term Performance of the Solution
˙Solution Replacement/Phase out

◆案例與演練

˙課程回顧與評量
˙各單元案例實作與分組討論 (Workshop)
˙模擬試題解題 (Mock Exam)

詳細課程內容請參考以下網址：http://www.iiiedu.org.tw/ites/AIIS.htm

- 新聞稿有效日期，至2019/01/21為止

上一篇：【資策會】CBAP國際商業分析師認證班 (台北3/10)
下一篇：【資策會】人工智慧影像辨識與解讀設計 (台北2/14)