SlideShare a Scribd company logo
1 of 22
MACHINE LEARNING
BASICS
ANTONIO FERNANDES, M.D.
NEURORADIOLOGIST, DEEP LEARNING
ENTHUSIASTIC IN BRAIN AND SPINE IMAGING
Machine Learning
 ML is a method of data analysis that incorporates the utilization of algorithms
that have the capabilities to learn from data without programming
 Computer science svvvv AI (a branch CS) ML (application of AI)
Machine Learning: GET SIMPLE!
 The world is full of data. Then use algorithms to predict and work for you. YOU
CAN NOT AVOID ML
 Machines and computers now do not need to have every detail programmed.
They can be programmed to learn by themselves and to work more efficiently.
 Human mind is multitasking and flexible. Computes are not yet there but each
year they are capable of doing more and more complex things
Neural Networks
 Neural Networks can looks like science fiction but is too real.
 NN are a series of mathematical formulas (algorithms) mimicking human brains
 NN can constantly adapt to new information and changes
 Using NN computers constantly adapt and don’t follow the always the same
instruction (mimicking brains- At least some brains!!)
Neural Networks -Brain
HUMAN GAIN
EXPERIENCE BY
THE 5 SENSES
THE BRAIN PROCESSES THE
INFORMATION AND
COMPARE WITH PREVIOUS
EXPERIENCES
CONLCUSION
SIMILAR TO
ML AND NN
PASSWAYS
OF THINKING
are constantly
shifting
between
billions of
neurons
DATA, KNOWLEDGE, ALGORITHMS
 Data is one resource that continues to grow
 AI turns Data into knowledge since in the past human being would be needed to
analyze large amounts of data.
 Algorithms – instead of a rigid code the data becomes parts of an algorithm and
the machine creates its own reasoning
 Example of algorithm: the email can be send to spam, social etc based on
different patterns that are constantly chancing
3 Types of ML
 SUPERVISED LEARNING – requires an input of data. Supervised because it requires human input to ensure the computer has the
right data. The goal is to learn from “labelled data”.
 (Classification - goal of predicting under which class new instances would be place e.g. spam email)
 (Regression – predict of continuous outcomes e.g. Analyzis of the length of study for SAT and the score for a population of students)
 UNSUPERVISED LEARNING – the computer does not have all the information to make a decision. May have some data.
 (Clustering – technique which let us organize a great amount of data into subgroup or clusters. E.g. marketers use this to determine
specific customer groups)
 (Dimensionality Reduction – compress the data sot it fits into a smaller subspace while keeping the relevant information intact)
 (Semi-supervised –blend of supervised and reinforcement learning).
 REINFORCEMENT LEARNING – goal is to develop a system that can improve its performance. The computer knows when to move
but will readjust it when it does some mistakes. E.g. Chess (the move depends on the environment).
PROCESS/training models
 Preparation (pre-processing) the raw data is the most important step of any ML
application.
 Important to choose the correct model between different algorithms: How can we
do that? We should have a training dataset and a validation dataset.
 The parameters should only be obtained from the training dataset and then
applied to the test dataset.
.
PROBLEMS OF MACHINE
LEARNING
ISSUES/PROBLEMS OF ML
 ML is still evolving and still being used every day
 E.g.1 Natural Language Processing – because different languages and accents –
challenges for Cortana, Alexa and Siri.
 With stabilized reinforcement learning the ability to control robotics would open
up endless possibilities
 GAN-Generative Adversarial Networks-set of algorithms implemented in 2 NN
working against each other. But they can crash!
 ML does not have many problems but it is still in its infancy
Problems with ML not yet solved
 Variable event space
 Processing languages – there is no context understanding yet.
 Facial identification –not yet perfect e.g. doesn’t recognize a female with makeup
 Automated learning is a big part of ML: Leaning has to come from a variety of
resources. E.g. IBM Watson
 3 way human rule not yet achieved by ML: take an image, gives it a type and then
gives it a description.
 A lot of memory space is need to collect all the data
Examples of problems solved
 Most of email spam actually goes to spam
 ML can learn about your credit card spending and if something is not usual can
alert as stolen
 ML can read post codes in envelopes
 Facial recognition to unlock the device, passports at the airport
 Similar suggestions by Amazon (Website algorithm)
 Babylon for symptoms
 Stocks: when to hold, buy or sell
Examples of problems solved
 Most of email spam actually goes to spam
 ML can learn about your credit card spending and if something is not usual can
alert as stolen
 ML can read post codes in envelopes
 Facial recognition to unlock the device, passports at the airport
 Similar suggestions by Amazon (Website algorithm)
 Babylon for symptoms
 Stocks: when to hold, buy or sell
Where ML is used
 Autopilot airplanes
 Search engines
 Language translation
 Facebook newsfeed is personalized for you as well as You Tube, Amazon
 IMPORTANT: If you have a large dataset in your organization, high quality and
then use it to improve.
The concept of Neural Networks
 Similar to neurons in Brain, with inter-conextions.
 Several layers of this neurons and each layer has its own purpose.
 TYPES OF NN
 A) CONVOLUTIONAL NEURAL NETWORKS (CNN)
 Your brain can instantly recognize a photo of your mother or a bird for instances. For computers
this is complex and they have to use CNN
 Used for image recognition, because it adapts the algorithms.
 B) PERCEPTION (binary function that produces 1 or zero) AND BACKPROPAGATION ( gradient
moves from the last layer till the first layer. Basically goes back to correct the errors. It is a trial
and error method. Uses successive iteration (or attempt).
Neural Networks and AI
 AI is the science of developing machines that have the ability to constantly
increase their intelligence.
 Computers can learn but not think. To try to overcome those obstacles a unique
form of ML has been developed – this is AI
 Some tasks such as identify text is so commonplace that is no longer consider AI.
Computers said to have AI are those that are able to play chess, self-driving-cars
etc
AI and Medicine
 E.g. IBM Watson -cognitive computer used for healthcare.
 Areas:
 - Data management
– choose the right therapy for cancer
- -The Deep Genomics – doctors can find what is inside the cells
- -speed up the clinical trials
- -recognizing patterns of radiology images
AI and Finance
 E.g. Weathfront – analyses the patter of spending and gives advice
 JP Morgan uses AI to extract important data from legal documents saving
annually 360 000 hours of manpower
 AI is in most of the finance companies to save money and increase revenue
 AI used to calculate parameters beyond human capacities
 Get important information from contracts
 Inspections that goes beyond human accuracy
- COUNTLESS APLICATIONS
AI in translation and game playing
TRANSLATION
 Machine makes clusters of words e.g. trees and leaves and this pattern is similar
in different languages.
 A way to test and learn is translate from language A to B and than back from B to
A. If it is different the machine self corrects.
GAMING
The gaming world is the safest environment where scientific problem solving can
work in harmony with creativity.
Using AI two players can be in different part of the world.
Deep Learning
 Sub-type of AI using Neural Networks
 With Deep Learning the computer is capable of making continuous adjustments
in order to improve its performance every time it is used
 E.g. Google to predict what websites you will must likely to visit
 Deep learning – e.g. automatically create a record of the number of vehicles that
pass thought a certain point on a public road (categorize the model, the maker,
the colour etc –difficult for an human to be standing taking care of the task.
 Pattern recognition – e.g. to expand the internet of things by collecting data from
any device that is connected to the internet.
Challenges
 The most advanced NN are pretty primitive when compared to the human brain
 Delta Rule- most common rule to train a NN. The input and output vectors are
compared and results adjusted using different algorithms that are already in the
system.
IMPORTANT NOTE
 Machine Learning for Beginners. Guide to understanding Machine Learning.
Matthew Kinsey. 2018.
 This presentation is a brief summary using sentences of the book above and is
used without any permition of the trademarks, brands or authors. This is for
clarifying purposes only.
 Do you want to join a Deep Learning Research Project/Start-up in Radiology:
email me please: afernandes@s24global.com

More Related Content

What's hot

What's hot (20)

Introduction to Artificial Intelligence.pptx
Introduction to Artificial Intelligence.pptxIntroduction to Artificial Intelligence.pptx
Introduction to Artificial Intelligence.pptx
 
Artificial intelligence : what it is
Artificial intelligence : what it isArtificial intelligence : what it is
Artificial intelligence : what it is
 
AI
AIAI
AI
 
Artificial inteligence
Artificial inteligenceArtificial inteligence
Artificial inteligence
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Artificial Intelligence and Machine Learning
Artificial Intelligence and Machine LearningArtificial Intelligence and Machine Learning
Artificial Intelligence and Machine Learning
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
PPT on Artificial Intelligence(A.I.)
PPT on Artificial Intelligence(A.I.) PPT on Artificial Intelligence(A.I.)
PPT on Artificial Intelligence(A.I.)
 
An Overview of Artificial intelligence (Part 1)
An Overview of Artificial intelligence (Part 1)An Overview of Artificial intelligence (Part 1)
An Overview of Artificial intelligence (Part 1)
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
Types Of Artificial Intelligence | Edureka
Types Of Artificial Intelligence | EdurekaTypes Of Artificial Intelligence | Edureka
Types Of Artificial Intelligence | Edureka
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Introduction to ai
Introduction to aiIntroduction to ai
Introduction to ai
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
Generative AI and law.pptx
Generative AI and law.pptxGenerative AI and law.pptx
Generative AI and law.pptx
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Artificial intelligence - An Overview
Artificial intelligence - An OverviewArtificial intelligence - An Overview
Artificial intelligence - An Overview
 

Similar to Artificial intelligence slides beginners

Everything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionEverything You Need to Know About Computer Vision
Everything You Need to Know About Computer Vision
Kavika Roy
 
Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
eswaralaldevadoss
 

Similar to Artificial intelligence slides beginners (20)

machine learning
machine learningmachine learning
machine learning
 
Webinar trends in machine learning ce adar july 9 2020 susan mckeever
Webinar trends in machine learning ce adar july 9 2020 susan mckeeverWebinar trends in machine learning ce adar july 9 2020 susan mckeever
Webinar trends in machine learning ce adar july 9 2020 susan mckeever
 
The Ultimate Guide to Machine Learning (ML)
The Ultimate Guide to Machine Learning (ML)The Ultimate Guide to Machine Learning (ML)
The Ultimate Guide to Machine Learning (ML)
 
Everything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionEverything You Need to Know About Computer Vision
Everything You Need to Know About Computer Vision
 
AI | Explore Machine Learning
AI | Explore Machine LearningAI | Explore Machine Learning
AI | Explore Machine Learning
 
Data science dec ppt
Data science dec pptData science dec ppt
Data science dec ppt
 
Machine learning introduction
Machine learning introductionMachine learning introduction
Machine learning introduction
 
Machine Learning Ch 1.ppt
Machine Learning Ch 1.pptMachine Learning Ch 1.ppt
Machine Learning Ch 1.ppt
 
Lect 7 intro to M.L..pdf
Lect 7 intro to M.L..pdfLect 7 intro to M.L..pdf
Lect 7 intro to M.L..pdf
 
Ai artificial intelligence professional vocabulary collection
Ai artificial intelligence professional vocabulary collectionAi artificial intelligence professional vocabulary collection
Ai artificial intelligence professional vocabulary collection
 
Deep learning
Deep learningDeep learning
Deep learning
 
Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
Unlocking the Potential of Artificial Intelligence_ Machine Learning in Pract...
 
Artificial_intelligence.pptx
Artificial_intelligence.pptxArtificial_intelligence.pptx
Artificial_intelligence.pptx
 
Machine learning
Machine learningMachine learning
Machine learning
 
A quick guide to artificial intelligence working - Techahead
A quick guide to artificial intelligence working - TechaheadA quick guide to artificial intelligence working - Techahead
A quick guide to artificial intelligence working - Techahead
 
Intro/Overview on Machine Learning Presentation
Intro/Overview on Machine Learning PresentationIntro/Overview on Machine Learning Presentation
Intro/Overview on Machine Learning Presentation
 
ARTIFICIAL INTELLIGENCE-New.pptx
ARTIFICIAL INTELLIGENCE-New.pptxARTIFICIAL INTELLIGENCE-New.pptx
ARTIFICIAL INTELLIGENCE-New.pptx
 
Machine learning
Machine learningMachine learning
Machine learning
 
Supervised Machine Learning Techniques common algorithms and its application
Supervised Machine Learning Techniques common algorithms and its applicationSupervised Machine Learning Techniques common algorithms and its application
Supervised Machine Learning Techniques common algorithms and its application
 
Intro to machine learning
Intro to machine learningIntro to machine learning
Intro to machine learning
 

Recently uploaded

Ernakulam Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Ernakulam Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetErnakulam Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Ernakulam Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Chandigarh
 
💚 Punjabi Call Girls In Chandigarh 💯Lucky 🔝8868886958🔝Call Girl In Chandigarh
💚 Punjabi Call Girls In Chandigarh 💯Lucky 🔝8868886958🔝Call Girl In Chandigarh💚 Punjabi Call Girls In Chandigarh 💯Lucky 🔝8868886958🔝Call Girl In Chandigarh
💚 Punjabi Call Girls In Chandigarh 💯Lucky 🔝8868886958🔝Call Girl In Chandigarh
Sheetaleventcompany
 
neemuch Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
neemuch Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetneemuch Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
neemuch Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Service
 
raisen Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
raisen Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetraisen Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
raisen Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Service
 
Sambalpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Sambalpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetSambalpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Sambalpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Service
 
ooty Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
ooty Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetooty Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
ooty Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Service
 
Tirupati Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Tirupati Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetTirupati Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Tirupati Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Service
 
palanpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
palanpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetpalanpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
palanpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Service
 
Mangalore Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Mangalore Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetMangalore Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Mangalore Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Service
 
kochi Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
kochi Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetkochi Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
kochi Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Service
 
nagpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
nagpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetnagpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
nagpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Service
 
Call Girl in Bangalore 9632137771 {LowPrice} ❤️ (Navya) Bangalore Call Girls ...
Call Girl in Bangalore 9632137771 {LowPrice} ❤️ (Navya) Bangalore Call Girls ...Call Girl in Bangalore 9632137771 {LowPrice} ❤️ (Navya) Bangalore Call Girls ...
Call Girl in Bangalore 9632137771 {LowPrice} ❤️ (Navya) Bangalore Call Girls ...
mahaiklolahd
 
kozhikode Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
kozhikode Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetkozhikode Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
kozhikode Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Service
 
Call Girl in Indore 8827247818 {Low Price}👉 Nitya Indore Call Girls * ITRG...
Call Girl in Indore 8827247818 {Low Price}👉   Nitya Indore Call Girls  * ITRG...Call Girl in Indore 8827247818 {Low Price}👉   Nitya Indore Call Girls  * ITRG...
Call Girl in Indore 8827247818 {Low Price}👉 Nitya Indore Call Girls * ITRG...
mahaiklolahd
 
Bareilly Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Bareilly Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetBareilly Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Bareilly Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Call Girls Service
 

Recently uploaded (20)

Ernakulam Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Ernakulam Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetErnakulam Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Ernakulam Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
Sexy Call Girl Dharmapuri Arshi 💚9058824046💚 Dharmapuri Escort Service
Sexy Call Girl Dharmapuri Arshi 💚9058824046💚 Dharmapuri Escort ServiceSexy Call Girl Dharmapuri Arshi 💚9058824046💚 Dharmapuri Escort Service
Sexy Call Girl Dharmapuri Arshi 💚9058824046💚 Dharmapuri Escort Service
 
💚 Punjabi Call Girls In Chandigarh 💯Lucky 🔝8868886958🔝Call Girl In Chandigarh
💚 Punjabi Call Girls In Chandigarh 💯Lucky 🔝8868886958🔝Call Girl In Chandigarh💚 Punjabi Call Girls In Chandigarh 💯Lucky 🔝8868886958🔝Call Girl In Chandigarh
💚 Punjabi Call Girls In Chandigarh 💯Lucky 🔝8868886958🔝Call Girl In Chandigarh
 
Kolkata Call Girls Miss Inaaya ❤️ at @30% discount Everyday Call girl
Kolkata Call Girls Miss Inaaya ❤️ at @30% discount Everyday Call girlKolkata Call Girls Miss Inaaya ❤️ at @30% discount Everyday Call girl
Kolkata Call Girls Miss Inaaya ❤️ at @30% discount Everyday Call girl
 
neemuch Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
neemuch Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetneemuch Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
neemuch Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
raisen Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
raisen Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetraisen Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
raisen Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
Sambalpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Sambalpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetSambalpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Sambalpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
ooty Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
ooty Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetooty Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
ooty Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
Tirupati Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Tirupati Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetTirupati Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Tirupati Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
palanpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
palanpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetpalanpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
palanpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
Mangalore Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Mangalore Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetMangalore Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Mangalore Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
kochi Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
kochi Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetkochi Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
kochi Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
(Deeksha) 💓 9920725232 💓High Profile Call Girls Navi Mumbai You Can Get The S...
(Deeksha) 💓 9920725232 💓High Profile Call Girls Navi Mumbai You Can Get The S...(Deeksha) 💓 9920725232 💓High Profile Call Girls Navi Mumbai You Can Get The S...
(Deeksha) 💓 9920725232 💓High Profile Call Girls Navi Mumbai You Can Get The S...
 
nagpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
nagpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetnagpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
nagpur Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
Call Girl in Bangalore 9632137771 {LowPrice} ❤️ (Navya) Bangalore Call Girls ...
Call Girl in Bangalore 9632137771 {LowPrice} ❤️ (Navya) Bangalore Call Girls ...Call Girl in Bangalore 9632137771 {LowPrice} ❤️ (Navya) Bangalore Call Girls ...
Call Girl in Bangalore 9632137771 {LowPrice} ❤️ (Navya) Bangalore Call Girls ...
 
Independent Call Girls Hyderabad 💋 9352988975 💋 Genuine WhatsApp Number for R...
Independent Call Girls Hyderabad 💋 9352988975 💋 Genuine WhatsApp Number for R...Independent Call Girls Hyderabad 💋 9352988975 💋 Genuine WhatsApp Number for R...
Independent Call Girls Hyderabad 💋 9352988975 💋 Genuine WhatsApp Number for R...
 
kozhikode Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
kozhikode Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meetkozhikode Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
kozhikode Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
Call Girl in Indore 8827247818 {Low Price}👉 Nitya Indore Call Girls * ITRG...
Call Girl in Indore 8827247818 {Low Price}👉   Nitya Indore Call Girls  * ITRG...Call Girl in Indore 8827247818 {Low Price}👉   Nitya Indore Call Girls  * ITRG...
Call Girl in Indore 8827247818 {Low Price}👉 Nitya Indore Call Girls * ITRG...
 
Bareilly Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Bareilly Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetBareilly Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Bareilly Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
Escorts Service Ahmedabad🌹6367187148 🌹 No Need For Advance Payments
Escorts Service Ahmedabad🌹6367187148 🌹 No Need For Advance PaymentsEscorts Service Ahmedabad🌹6367187148 🌹 No Need For Advance Payments
Escorts Service Ahmedabad🌹6367187148 🌹 No Need For Advance Payments
 

Artificial intelligence slides beginners

  • 1. MACHINE LEARNING BASICS ANTONIO FERNANDES, M.D. NEURORADIOLOGIST, DEEP LEARNING ENTHUSIASTIC IN BRAIN AND SPINE IMAGING
  • 2. Machine Learning  ML is a method of data analysis that incorporates the utilization of algorithms that have the capabilities to learn from data without programming  Computer science svvvv AI (a branch CS) ML (application of AI)
  • 3. Machine Learning: GET SIMPLE!  The world is full of data. Then use algorithms to predict and work for you. YOU CAN NOT AVOID ML  Machines and computers now do not need to have every detail programmed. They can be programmed to learn by themselves and to work more efficiently.  Human mind is multitasking and flexible. Computes are not yet there but each year they are capable of doing more and more complex things
  • 4. Neural Networks  Neural Networks can looks like science fiction but is too real.  NN are a series of mathematical formulas (algorithms) mimicking human brains  NN can constantly adapt to new information and changes  Using NN computers constantly adapt and don’t follow the always the same instruction (mimicking brains- At least some brains!!)
  • 5. Neural Networks -Brain HUMAN GAIN EXPERIENCE BY THE 5 SENSES THE BRAIN PROCESSES THE INFORMATION AND COMPARE WITH PREVIOUS EXPERIENCES CONLCUSION SIMILAR TO ML AND NN PASSWAYS OF THINKING are constantly shifting between billions of neurons
  • 6. DATA, KNOWLEDGE, ALGORITHMS  Data is one resource that continues to grow  AI turns Data into knowledge since in the past human being would be needed to analyze large amounts of data.  Algorithms – instead of a rigid code the data becomes parts of an algorithm and the machine creates its own reasoning  Example of algorithm: the email can be send to spam, social etc based on different patterns that are constantly chancing
  • 7. 3 Types of ML  SUPERVISED LEARNING – requires an input of data. Supervised because it requires human input to ensure the computer has the right data. The goal is to learn from “labelled data”.  (Classification - goal of predicting under which class new instances would be place e.g. spam email)  (Regression – predict of continuous outcomes e.g. Analyzis of the length of study for SAT and the score for a population of students)  UNSUPERVISED LEARNING – the computer does not have all the information to make a decision. May have some data.  (Clustering – technique which let us organize a great amount of data into subgroup or clusters. E.g. marketers use this to determine specific customer groups)  (Dimensionality Reduction – compress the data sot it fits into a smaller subspace while keeping the relevant information intact)  (Semi-supervised –blend of supervised and reinforcement learning).  REINFORCEMENT LEARNING – goal is to develop a system that can improve its performance. The computer knows when to move but will readjust it when it does some mistakes. E.g. Chess (the move depends on the environment).
  • 8. PROCESS/training models  Preparation (pre-processing) the raw data is the most important step of any ML application.  Important to choose the correct model between different algorithms: How can we do that? We should have a training dataset and a validation dataset.  The parameters should only be obtained from the training dataset and then applied to the test dataset.
  • 10. ISSUES/PROBLEMS OF ML  ML is still evolving and still being used every day  E.g.1 Natural Language Processing – because different languages and accents – challenges for Cortana, Alexa and Siri.  With stabilized reinforcement learning the ability to control robotics would open up endless possibilities  GAN-Generative Adversarial Networks-set of algorithms implemented in 2 NN working against each other. But they can crash!  ML does not have many problems but it is still in its infancy
  • 11. Problems with ML not yet solved  Variable event space  Processing languages – there is no context understanding yet.  Facial identification –not yet perfect e.g. doesn’t recognize a female with makeup  Automated learning is a big part of ML: Leaning has to come from a variety of resources. E.g. IBM Watson  3 way human rule not yet achieved by ML: take an image, gives it a type and then gives it a description.  A lot of memory space is need to collect all the data
  • 12. Examples of problems solved  Most of email spam actually goes to spam  ML can learn about your credit card spending and if something is not usual can alert as stolen  ML can read post codes in envelopes  Facial recognition to unlock the device, passports at the airport  Similar suggestions by Amazon (Website algorithm)  Babylon for symptoms  Stocks: when to hold, buy or sell
  • 13. Examples of problems solved  Most of email spam actually goes to spam  ML can learn about your credit card spending and if something is not usual can alert as stolen  ML can read post codes in envelopes  Facial recognition to unlock the device, passports at the airport  Similar suggestions by Amazon (Website algorithm)  Babylon for symptoms  Stocks: when to hold, buy or sell
  • 14. Where ML is used  Autopilot airplanes  Search engines  Language translation  Facebook newsfeed is personalized for you as well as You Tube, Amazon  IMPORTANT: If you have a large dataset in your organization, high quality and then use it to improve.
  • 15. The concept of Neural Networks  Similar to neurons in Brain, with inter-conextions.  Several layers of this neurons and each layer has its own purpose.  TYPES OF NN  A) CONVOLUTIONAL NEURAL NETWORKS (CNN)  Your brain can instantly recognize a photo of your mother or a bird for instances. For computers this is complex and they have to use CNN  Used for image recognition, because it adapts the algorithms.  B) PERCEPTION (binary function that produces 1 or zero) AND BACKPROPAGATION ( gradient moves from the last layer till the first layer. Basically goes back to correct the errors. It is a trial and error method. Uses successive iteration (or attempt).
  • 16. Neural Networks and AI  AI is the science of developing machines that have the ability to constantly increase their intelligence.  Computers can learn but not think. To try to overcome those obstacles a unique form of ML has been developed – this is AI  Some tasks such as identify text is so commonplace that is no longer consider AI. Computers said to have AI are those that are able to play chess, self-driving-cars etc
  • 17. AI and Medicine  E.g. IBM Watson -cognitive computer used for healthcare.  Areas:  - Data management – choose the right therapy for cancer - -The Deep Genomics – doctors can find what is inside the cells - -speed up the clinical trials - -recognizing patterns of radiology images
  • 18. AI and Finance  E.g. Weathfront – analyses the patter of spending and gives advice  JP Morgan uses AI to extract important data from legal documents saving annually 360 000 hours of manpower  AI is in most of the finance companies to save money and increase revenue  AI used to calculate parameters beyond human capacities  Get important information from contracts  Inspections that goes beyond human accuracy - COUNTLESS APLICATIONS
  • 19. AI in translation and game playing TRANSLATION  Machine makes clusters of words e.g. trees and leaves and this pattern is similar in different languages.  A way to test and learn is translate from language A to B and than back from B to A. If it is different the machine self corrects. GAMING The gaming world is the safest environment where scientific problem solving can work in harmony with creativity. Using AI two players can be in different part of the world.
  • 20. Deep Learning  Sub-type of AI using Neural Networks  With Deep Learning the computer is capable of making continuous adjustments in order to improve its performance every time it is used  E.g. Google to predict what websites you will must likely to visit  Deep learning – e.g. automatically create a record of the number of vehicles that pass thought a certain point on a public road (categorize the model, the maker, the colour etc –difficult for an human to be standing taking care of the task.  Pattern recognition – e.g. to expand the internet of things by collecting data from any device that is connected to the internet.
  • 21. Challenges  The most advanced NN are pretty primitive when compared to the human brain  Delta Rule- most common rule to train a NN. The input and output vectors are compared and results adjusted using different algorithms that are already in the system.
  • 22. IMPORTANT NOTE  Machine Learning for Beginners. Guide to understanding Machine Learning. Matthew Kinsey. 2018.  This presentation is a brief summary using sentences of the book above and is used without any permition of the trademarks, brands or authors. This is for clarifying purposes only.  Do you want to join a Deep Learning Research Project/Start-up in Radiology: email me please: afernandes@s24global.com