Détails
- 20 Sections
- 49 Lessons
- 5 Days
Expand all sectionsCollapse all sections
- Introduction to AI, ML & DL4
- 1.1DL as an approach to AI
- 1.2Neural Networks and Types
- 1.3Data Types
- 1.4Strengths and Limits of ML
- Sample Toy Study2
- 2.1Image recognition
- 2.2Complex regressions Use Case
- AI Frameworks1
- 3.1Keras as Reference & Doc Framework
- Framework Setup & Workshop2
- 4.1PyTorch installation and Setup
- 4.2Toy-study in Pytorch
- Introduction to NLP6
- 5.1NLP and Applications
- 5.2Data Cleaning & Preprocessing
- 5.3Tokenization
- 5.4Stop-words, stemming & lemmatization
- 5.5Text Data Vectorization
- 5.6BERT, Transformers (and Adapters)
- Classification & Clustering2
- 6.1Theory
- 6.2KNN, K-Means
- NLP Sample Toy Study1
- 7.1Text classification & clustering (using scikit-learn)
- Interactive Discussion1
- 8.1Put the toy-study results into test
- Additional Supervised & Unsupervised methods3
- 9.1Supplemental Methods to be defined
- 9.2Model selection and evaluation
- 9.3Visualisation
- AI in Cybersecurity2
- 10.1Analytics based on data sources
- 10.2AI Topics in Cybersecurity
- NLP Applied to Cybersecurity5
- 11.1Introduction
- 11.2Network threat analysis
- 11.3Text Classification Methods to Detect Malware
- 11.4Process Behaviour Analysis
- 11.5Abnormal system behaviour detection
- Use Case 12
- 12.1Using ML to Detect Malicious URLs
- 12.2(Note: This can be replaced by a Transformers use-case: using a pre trained BERT model, i.e. from hugging face)
- Interactive Discussion1
- 13.1Performance discussion, visualisation and comparison
- Statistical Methods in ML3
- 14.1Intuition vs Statistics
- 14.2Univariate Numerical Analysis
- 14.3Bivariate Numerical Analysis
- Examples2
- 15.1Univariate (Mean, Median, Percentile, SD)
- 15.2Bivariate (Correlation, Pearson Correlation)
- More Statistics3
- 16.1Skewness & bias estimations
- 16.2(basic) Bayes & Max entropy methods
- 16.3Confidence Level approach
- Case 1 (Continuation)2
- 17.1Statistical Methods as a tool for performance hypothesis testing
- 17.2Improve the DL model’s performance
- AI in Cybersecurity (part 2)3
- 18.1Transaction fraud detection
- 18.2Text-based malicious intent detection
- 18.3Machine vs human differentiation – or – Business data risk classification
- Use Case 22
- 19.1Using ML as Intrusion Detection System
- 19.2ML for Same Person Identification (prefered choice)
- Revision & Closing2
- 20.1Interactive Multiple Choices Questions Revision
- 20.2Closing Words
