Professional Documents
Culture Documents
Centre de Recherche en Numérique de Sfax , Route de Tunis km 10 , Sakiet Ezzit , 3021 Sfax – Tunisie
About me
Assistant Professor at the Digital Research Center of Sfax, Tunisia
Head of the Brain4ICT team at the CRNS
Postdoctoral Researcher at National School of Engineering of Sfax, University of Sfax:
PRF Project 2017 – 2020: Multimodal Biometric Platform for fighting against the Terrorism in Tunisia;
PAQ Collabora Project 2019 – 2021: Identification of Radicalized Profiles of Young Tunisians on Social Networks;
PRF Project 2019 – 2021: Artificial Intelligence for facial dysmorphic identification for Tunisian newborns.
PRF Project 2020 – 2021: Dysmorphic Face analysis for Metabolic sundrom
Trainer on Machine Learning and Deep Learning:
University of Manouba (1);
DGET (ISETN) (2);
University of Sousse (3);
University of Monastir (3);
University of Sfax (2);
Spring and Summer Schools (2).
Lead Auditor ISO 9001:2015;
Past Regional Coordinator of the Sfax Smart City Living Lab (SSCLL);
1
08/11/2021
Brain4ICT’s Overview
Outline
Part I – Machine Learning tools for NLP
1. Artificial Intelligence (AI): from perception to reasoning
2. How to design and use a Machine Learning (ML) for NLP?
3. Machine Learning Techniques: A brief Review & Comparison
4. Neural Network: Theory and Application
5. Naïve Bayes: Theory and Application
6. Support Vector Machines (SVM): Theory and Application
7. How to select the appropriate Machine Learning
8. How to evaluate a Machine Learning Performance?
Part II – Natural Langage Processing (NLP) tools
9. Machine Learning (ML) for NLP?
10. Libraries & Frameworks
11. Cleaning Process
12. Word Embedding
13. Features Selection & Features Transformation
14. NLP Applications: Clustering & Classification Tasks
Wael Ouarda - CRNS 4
2
08/11/2021
Outline
Part III – Deep Learning tools for NLP
15. Convolutional Neural Network
16. Long Short Term Memory
17. CNN-LSTM for NLP
18. Transformers Vs Bert & Attentions in NLP
Part IV – Chatbots
19. Natural Language Understanding
20. Natural Language Generation
21. Chatbot form Scratch
22. Chatbot with Frameworks
Image
Perception Processing
Living beings
Optimization Bio-Inspired
Living beings Optimization
Learning Machine
Learning
Baby, Animal, etc.
3
08/11/2021
Features Classification
Preprocessing Features Representation
Datamining
Data Cleaning Features Selection
Database Sentiment Analysis
Data cleaning Data Engineering
Topic Modeling
Dataset
Model
Data 1 Data 2
Data 1 Data 2
Testing process
F(X|X=”I”)=P1
F(X/X=”II”)=P2
? Preprocessing max(P1,P2)
X?
Why Preprocessing?
3. Data mining
■ Missed values: not available data -> Replace missed values by zero, max, min, average, mediance, etc;
■ Mixed values: We find different types of columns
● Categorical, Object, String, etc -> Encoding data
● Numerical
4
08/11/2021
10
5
08/11/2021
Euclidian Distance
Similarity based
Cosine Distance
RNN
6
08/11/2021
F F
x F F
C1
y F F
C2
z F F
W1 F F W3
W2
W1 F F W3
W2
7
08/11/2021
F= Nonlinear Activation Function to insert a Non Linear Representation into Neural Network
-1
8
08/11/2021
0,5 1
2 1
-1 -1
1,5 3
-1 -3
-2 -4
0,5 1
2 ? 1
-1 -1
1,5 3
-1 -3
-2 -4
9
08/11/2021
0,5 1
2 0,378 1
-1 -1
1,5 3
-1 -3
-2 -4
0,5 1
2 0,378 1
-1 -1
1,5 3
-1 ? -3
-2 -4
10
08/11/2021
0,5 1
2 0,378 ? 1
-1 -1
1,5 3
-1 0,5 -3
-2 -4
0,5 1
2 0,378 0,876 1
-1 -1
1,5 3
-1 0,5 0,085 -3
-2 -4
11
08/11/2021
0,5 1
2 0,378 0,876 1
-1 -1
0,648
1,5 3
-1 0,5 0,085 -3
-2 -4
0,5 1
2 0,378 0,876 1
Δ = 1 – 0,648 = 0,352
-1 -1
0,648
1,5 3
-1 0,5 0,085 -3
-2 -4
12
08/11/2021
Δ = 0,041
0,5 1
2 0,378 0,876 1
Δ = 0,352
-1 -1
0,648
1,5 3
-1 0,5 0,085 -3
-2 -4
Δ = 0,041
0,5 1
2 0,378 0,876 1
Δ = 0,352
-1 -1
0,648
1,5 3 Δ = −0,082
-1 0,5 0,085 -3
-2 -4
13
08/11/2021
Δ = 0,041
Δ
0,5 1
2 0,378 0,876 1
Δ = 0,352
-1 -1
0,648
1,5 3 Δ = −0,082
-1 0,5 0,085 -3
-2 -4
Δ = 0,029 Δ = 0,041
0,5 1
2 0,378 0,876 1
Δ = 0,352
-1 -1
0,648
Δ Δ = −0,082
1,5 3
-1 0,5 0,085 -3
-2 -4
14
08/11/2021
Δ = 0,029 Δ = 0,041
0,5 1
2 0,378 0,876 1
Δ = 0,352
-1 -1
0,648
Δ = 0,113 3 Δ = −0,082
1,5
-1 0,5 0,085 -3
-2 -4
-1 0,5 0,085 -3
-2 -4
0,5 -> weight old value + α * neuron value * Delta of the next neuron
15
08/11/2021
-1 0,5 0,085 -3
-2 -4
0,5 -> weight old value + α * neuron value * Delta of the next neuron
-1 0,5 0,085 -3
-2 -4
16
08/11/2021
17
08/11/2021
Train Database
18
08/11/2021
19
08/11/2021
𝟓 𝟓
𝑷 𝑵𝒐 = 𝑷 𝒀𝒆𝒔 =
𝟏𝟎 𝟏𝟎
Sample X= <Red, Classic, Domicile>
Color
𝟑 𝟐
𝑷 𝑿/𝒀𝒆𝒔 = 𝑷 𝑹𝒆𝒅/𝒀𝒆𝒔 x 𝑷 𝑪𝒍𝒂𝒔𝒔𝒊𝒄/𝒀𝒆𝒔 x 𝑷 𝑫𝒐𝒎𝒊𝒄𝒊𝒍𝒆/𝒀𝒆𝒔 x 𝑷 𝒀𝒆𝒔 𝑷 𝑹𝒆𝒅/𝒀𝒆𝒔 = 𝑷 𝒀𝒆𝒍𝒍𝒐𝒘/𝒀𝒆𝒔 =
𝟓 𝟓
𝟑 𝟏 𝟐 𝟓 𝟐 𝟑
= ∗ ∗ ∗ 𝑷 𝑹𝒆𝒅/𝑵𝒐 = 𝑷 𝒀𝒆𝒍𝒍𝒐𝒘/𝑵𝒐 =
𝟓 𝟓 𝟓 𝟏𝟎
𝟓 𝟓
Basic Idea: Find the appropriate Support Vector which maximize Margin Distance
M1
M2
M1 + M2 = Margin Distance
20
08/11/2021
Basic Idea: Find the appropriate Support Vector which maximize Margin Distance
Class A
Class B
M1
M2
Class B
Support Vector SV: A.X + B Support Vector SV: F(X)
F is a non linear Function
Basic Idea: Find the appropriate Support Vector which maximize Margin Distance
Class A
Class B
M1
M2
Class B
Support Vector SV: A.X + B Support Vector SV: F(X)
F is a non linear Function
21
08/11/2021
Class B
Kernel
Class C
Class D
Kernel
22
08/11/2021
23
08/11/2021
65
35
𝑅𝑒𝑐𝑎𝑙𝑙 ∗ 𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛
𝐹1 − 𝑠𝑐𝑜𝑟𝑒 = 2 ∗
𝑅𝑒𝑐𝑎𝑙𝑙 + 𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛
𝑔 = (𝑅𝑒𝑐𝑎𝑙𝑙 ∗ 𝑃𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛)
24