See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/351412945

Introduction to Artificial Intelligence for beginners

Presentation · May 2021

DOI: 10.13140/RG.2.2.24577.38244

CITATIONS READS

0 71

1 author:

Israël Tankam Chedjou

University of Cambridge
14 PUBLICATIONS   26 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Modelling and control plantain plant-parasitic nematodes View project

African Artificial Intelligence Society - Projects View project

All content following this page was uploaded by Israël Tankam Chedjou on 08 May 2021.

The user has requested enhancement of the downloaded file.

 Israël Tankam C.

Introduction to AI for beginners

 “Worrying about AI evil superintelligence today is like worrying
about overpopulation on the planet Mars. We haven't even landed
on the planet yet!”
Andrew Ng
Contents
01 What is (not) AI ?

Use cases of AI
02
03 AI Careers
What is (not) AI ?
 Artificial Intelligence (AI)
What is Artificial Intelligence (AI)?

• Using computers to solve problems

• Or make automated decisions

• For tasks that, when done by humans,

• Typically require intelligence
 Limits of Artificial Intelligence
• “Strong” Artificial Intelligence ✘
• Computers thinking at a level that meets or surpasses people
• Computers engaging in abstract reasoning & thinking
• This is not what we have today
• There is no evidence that we are close to Strong AI

• “Weak” Pattern-Based Artificial Intelligence ✔

• Computers solve problems by detecting useful patterns
• Pattern-based AI is an Extremely powerful tool
• Has been used to automate many processes today
• Driving, language translation, classification, art-generation, etc.
• This is the dominant mode of AI today
 Major AI Approaches
Two Major AI Techniques
• Logic and Rules-Based Approach

• Machine Learning (Pattern-Based Approach)

 Logic and Rules-Based Approach
• Logic and Rules-Based Approach
• Representing processes or systems using logical rules
• Top-down rules are created for computer
• Computers reason about those rules
• Can be used to automate processes

• Example within archive management

• Izysearch
• archive and structure digitized documents
• Represented as logical computer rules
• Software analyzes contents
 Machine Learning (Pattern based)
•Machine Learning (ML)
• Algorithms find patterns in data and infer rules on their own
• ”Learn” from data and improve over time
• These patterns can be used for automation or prediction
• ML is the dominant mode of AI today

Statistics

Cognitive Computer
sciences sciences

Machine
Learning
Supervised learning
 The process
Input: Output:
Data Artificial Action
Sensors Intelligence Movement
Images… Text…

Machine Learning
Algorithm
Labelled Data
Training
Prediction

Learned Model Prediction

Data
The data
Overfitting
Overfitting
Underfitting
Bias/Variance compromise
Bias/Variance compromise
 Which data ?
Training data Validation data Test data

Should come from the same distribution

 Which data ?
Training data Validation data Test data

Should come from the same distribution

 Which data ?
Training data Validation data Test data

Should come from the same distribution

 Example
Which features ?
Sector Category Years of ex. Level Salary
Set of all
features BTP A1 6 2 160,000
Teaching A2 3 1 180,000
BTP B2 2 1 135,000
Admin. A1 5 3 180,000
Selecting the
best subset Teaching A2 19 4 210,000
Teaching A1 8 4 180,000
Teaching B2 1 1 120,000
Machine
learning
algorithm

ACP
Performance
or
New Feature Just Salary
Unsupervised learning
Reinforcement learning
1. The input and output
system

2. The reward

3. The AI environment

4. The Markov decision

process

5. Training and inference

 The learning phase

gradient descent
 In practice
1- Collect and prepare the data
2- Built your first model quick and train it on
the data
3- Create a single measure of accuracy
4- Test the accuracy of your model on
ground truth data
5- Modify the model to have better accuracy
• Solve variance or bias problems
• Have more data for training
• Train longer
• Regularize
• Dropout
• Deeper or shallower models
• Etc.
6- Train the new model
Summary: the machine learning pipeline
Data
Data collection Data
visualization
and integration preparation
and analysis

Model Feature
evaluation Model training selection and
(error analysis) engineering

Prediction
 The process (in details)
Re-training
ML problem framing Data collection

Monitoring & debugging

Feature engineering
Data integration

Data augmentation Model training &

Data preparation & Parameter tuning
Cleaning

Predictions
Model evaluation
Data visualization &
analysis

Model deployment
augmentation
Feature

No Are business Yes

goals met ?
Use cases of AI
Every industry wants intelligence
Robots… Obviously
Human-robot
interaction

Sophia the social robot

• Environmental
Robot displacement recognition
• Reinforcement learning • Natural language
processing
• Facial expression
processing
 Bank and finance
10 dimensional input
Composite Index
vector of volatility
Volatility Forecast
forecast for 10 indices

Consumer
Corporate
Wholesale
Credit risk
Credit card
Principal risk Concentration
Counterparty
Financial risk Collateral
Interest rate
Market risk Foreign exchange
Equity
Commodity
Liquidity risk Credit spread
Risk

Country risk Funding

Compliance Asset
risk
Conduct risk
Legal risk
Non-financial
risk Model risk Cyber security
Business & Fraud
strategic risk Vendor/Outsourcing
Reputational Technology resilience
risk
Unauthorized activity
Operational risk Financial crime
Military sector and intelligence services
Drones with brain
• Computer vision
• Decision making
• Etc.

• Profiling
• Sentiment analysis
• Context analysis
• Decision making
• Tactics
⚠ Social biases
 Health Care

Google DeepBlind
• identify the early signs of eye disease

AICure.com is one company that has created an

at-home AI assistant for medication tracking.
• Robot-Assisted Surgery ($40 billion industry)
• Virtual Nursing Assistants ($20 billion industry)
• Administrative Workflow Assistance ($18 billion
 Health Care
• Robot-Assisted Surgery ($40 billion
industry)
• Virtual Nursing Assistants ($20
billion industry)
• Administrative Workflow Assistance
($18 billion industry)
Robot-assisted healthcare
AI and Covid-19

• Contact tracing • Development of therapeutics

• Monitoring of COVID-19 cases
• Early diagnosis
• Reducing the burden from medical
practitioners & healthcare staff
• Protein structure prediction
• Development of vaccines
• Curbing spread of misinformation
• Genomics
Travel industry
• Hotel Bookings by Voice Command
• AI Concierge Services: Amazon
(Alexa), Apple (Siri)
• Travel Service Chatbots (NPL)
• Check-in Through Facial
Recognition
• Self-Driving Cars
• Other Robotic Tools: Hotels, tourism
offices, and other travel-based
businesses will soon be able to
employ robots in place of traditional
human workers
 Journalism
transforms pieces of data into
readable articles
(Natural Language Generation)

• AI discovers what makes various kinds of content popular

and engaging

• Audience targeting

• Speech analysis

• MOGIA : an indian startup successfully predicted 3 US

presidential election results
Education
• Personalized Learning Platforms

• Individualized AI Tutors

• Personalized Games

• Crafting a More Enjoyable

Learning Experience
 Agriculture
• Remote sensing yield prediction

Agricultural drones
• Monitor the growth and
production of crops
• Id. weeds and damaged
plants.
• Potential of a given terrain

• Autonomous tractors

Monitor plant growth

using sensors for light
and nutrients
Fun and utilities
Computer vision
Image captioning
Computer vision
Image compression
Computer vision
Adding features
Computer vision
Image colorization
Computer vision
Image-to-image
Computer vision
Style transfer
Generative Adversarial Networks

• Music generator
• Art generator
• Faces generator
• Architecture
• Object/animals/scenes generator
 GAN and NLP
Image Generation – From Descriptions
 GAN and NLP
Image Generation – Handwriting
Computer vision and NLP
LipNet - Sentence-level Lipreading
NLP for audio processing
Sound generation
Natural Language Processing
Syntax Parsing
Natural Language Processing
Generating text
Natural Language Processing
Translation
Natural Language Processing
Chatbot
 Email Spam Filter
Example • System detects patterns in Probability of spam
Email about likely markers
“Earn cash” of spam Contains Contains
• Can use such detected “Free” “Earn cash”
patterns to make 70% spam 90% spam
automated decisions
about
future emails

1. Algorithm improves in
“Earn cash” performance in auto- From
appears in 10% identifying spam Nigeria
Of spam emails, 2. Algorithm is “learning” 85% spam
0% of non-spam over time from additional
It’s a (generalizable) pattern examples
 Recommender systems
Content-based filtering Collaborative filtering

A content A content
genre genre

Similar users
Similar content

Recommend to user Watched by her, recommend to him

Activity: How do self-driving car work ?
There are many and many other examples
AI Careers
Data architect Data engineer Data analyst/ Data scientist ML engineer
Business analyst Query data,
Manages data Maintains the Create or choose
Makes graphs to implement
storage and its data, implements machine learning
visualize data and algorithms, make
infrastructure queries for the algorithms
queries graphics
database
Hadoop, Spark,
Hadoop, Spark, Hadoop, Spark, SQL/NoSQL, SQL/NoSQL,
Python, R, Stats
SQL/NoSQL SQL/NoSQL Excel, Tables Python, R,
Python Tables

graphs

database database Machine learning

algorithm

Query
database
 Others

Robot Engineer Robot Scientist Big Data Engineer

Business Analyst Research Scientist Product Manager

Skills
 Thanks for your time and attention !

@AiAfrican

Chat ? @israeltankam
View publication stats