/
Machine Learning for dotNET Developer Machine Learning for dotNET Developer

Machine Learning for dotNET Developer - PowerPoint Presentation

dollumbr
dollumbr . @dollumbr
Follow
342 views
Uploaded On 2020-06-16

Machine Learning for dotNET Developer - PPT Presentation

Bahrudin Hrnjica MVP Agenda Intro to ML Types of ML dotNET and MLtools and libraries Demo01 ANN with C Demo02 GP with C NET Tools AcordNET GPdotNET Summary Machine Learning method of teaching computers to make predictions based on data ID: 778483

data learning machine training learning data training machine net set optimization https accord testing gpdotnet supervised error ann github

Share:

Link:

Embed:

Download Presentation from below link

Download The PPT/PDF document "Machine Learning for dotNET Developer" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.


Presentation Transcript

Slide1

Slide2

Machine Learning for dotNET Developer

Bahrudin Hrnjica, MVP

Slide3

Agenda

Intro to ML

Types of ML

dotNET and ML-tools and libraries

Demo01: ANN with C#

Demo02: GP with C#

.NET Tools – Acord.NET, GPdotNET

Summary

Slide4

Machine Learning?

method of teaching computers to make predictions based on data.

branch of Artificial intelligence

semi-automated extraction of knowledge from data

always starts from data, and the goal is knowledge extraction,

involves some amount of automation in form of algorithm and computer to do the job,

not fully automated, it requires many smart decisions by a human.

Slide5

Traditional Programming

Machine Learning

Computer

Data

Program

Output

Computer

Data

Output

Program

Slide6

Magic?

No, more like gardening

Seeds

= Algorithms

Nutrients

= DataGardener = YouPlants = Programs

Slide7

Sample Applications

Web search

Engineering

Finance

E-commerce

Space exploration

RoboticsInformation extractionSocial networksDebugging[Your favorite area]

Slide8

ML in a Nutshell

Tens of thousands of machine learning algorithms

Hundreds new every year

Every machine learning algorithm has three components:

Representation

Evaluation

Optimization

Slide9

Representation

Chromosomes in genetics (GA/GP)

Neural networks

Decision trees

Sets of rules / Logic programs

Instances

Graphical models (Bayes/Markov nets)Support vector machinesEtc.

Slide10

Evaluation

Accuracy

Precision and recall

Squared error

Likelihood

Posterior probability

Cost / UtilityMarginEntropyK-L divergenceEtc.

Slide11

Optimization/Learners

Combinatorial optimization

E.g.: Greedy search

Convex optimization

E.g.: Gradient descent

Constrained optimization

E.g.: Linear programmingGeneral optimizationE.g.: Genetic AlgorithmE.g.: Particle Swarm Optimization

Slide12

Types of Learning

Supervised (inductive) learning

Training data includes desired outputs

Unsupervised learning

Training data does not include desired outputs

Semi-supervised learning

Training data includes a few desired outputs

Slide13

Machine learning structure

Supervised learning

Slide14

Machine learning structure

Unsupervised learning

Slide15

Training and testing

Training set

(observed)

Universal set

(unobserved)

Testing set

(unobserved)

Data acquisition

Practical usage

Slide16

Training and testing

Training is the process of making the system able to learn.

No free lunch rule:

Training set and testing set come from the same distribution

Need to make some assumptions or bias

Slide17

What are we seeking?

Supervised: Low E-out or maximize probabilistic terms

Unsupervised: Minimum quantization error, Minimum distance, MAP, MLE(maximum likelihood estimation)

E-in: for training set

E-out: for testing set

Slide18

What are we seeking?

Under-fitting

VS. Over-fitting

(fixed

N

)

error

(model = hypothesis + loss functions)

Slide19

dotNET and ML

Learning API -

https://github.com/UniversityOfAppliedSciencesFrankfurt/LearningApi

Accord .NET -

https://github.com/accord-net/framework

GPdotNET- https://github.com/bhrnjica/gpdotnet

Slide20

DEMO- Simple ANN and GP C# Program

IRIS DATA DEMO

Slide21

Accord .NET

Slide22

DEMO

ACCORD .NET

Slide23

LearningAPI

Slide24

GPdotNET

GP and ANN

Slide25

Existing ML tools are difficult or impossible to integrate into a software system.

Commercial and Open Source API libraries work well for some machine learning tasks but are extremely limited for neural networks.

To develop neural networks using Visual Studio you must understand seven core concepts: feed-forward, activation, data encoding, error, training, free parameters, and over-fitting.

Once the concepts are mastered, implementation with Visual Studio

is not difficult (but not easy either).

Slide26

Reference

http://bhrnjica.net/gpdotnet

http://accord-framework.net/

https://github.com/UniversityOfAppliedSciencesFrankfurt/LearningApi

http://www.quaetrix.com/Build2013.html

C# ANN sample

https://msdn.microsoft.com/en-us/magazine/mt149362?author=james+mccaffrey

Slide27

HVALA NA PAŽNJI!