1.- Intelligence & Learning - UPM · CVG-UPM COMPUTER VISION P. Campoy Machine Learning and Neural...

CVG-UPMC

Machine Learning and Neural NetworksP. CampoyP. CampoyP. Campoy

Machine Learning & Neural Networks

1.- Intelligence & Learning

byPascual Campoy

Computer Vision GroupC.A.R. - U.P.M.

CVG-UPM

Intelligence and learning

What is intelligence?

What are intelligent machines?

The learning relevance

Building intelligent machines

Objectives of the subject

Applications

CVG-UPMC

¿ What is intelligence ?

“Intelligence is a very general mental capabilitythat, among other things, involves the ability toreason, plan, solve problems, think abstractly,comprehend complex ideas, learn quickly andlearn from experience. […], it reflects a broaderand deeper capability for comprehending oursurroundings -- "catching on," "making sense" ofthings, or "figuring out" what to do”statement signed by 52 experts in intelligence in the WallStreet Journal & in the Intelligence Journal 1994

CVG-UPM

¿ What is intelligence ?

•“Prediction is the real essence of cerebralfunction”, Rodolfo Llinás “I and the vortex”

Recognition, prediction and learning

an intelligent machine has to recognize thesituation and predict the future based on

learned previous experiences

•“Intelligence is the capability of predictingfuture”, Jeff Hawkins “On Intelligence”

CVG-UPMC

¿ Machine intelligence ?

CVG-UPM

Alan Turing test:• original version: “a machine is said to beintelligent if it can fool a judge as often as aperson in pretending to be a man/woman”• later extended version: “a machine is saidto be intelligent if it can fool a judge to be aperson”

CVG-UPMC

CVG-UPM

•“Chinese room paradigm: suppose that amachine convinces a human Chinese speaker thatthe program is itself a human Chinese speaker, thenthe machine is substitute by a non Chinese speakingperson in a room provided with the same algorithmand information as the machine had. Does he/sheunderstand Chinese? ” de John Searle

CVG-UPMC

CVG-UPM

Learning relevance

imagen sólo para la imagen sólo para la mitad izquierda del mitad izquierda del

auditorioauditorio

imagen sólo para la imagen sólo para la mitad derecha del mitad derecha del

auditorioauditorio

CVG-UPMC

learning relevance

CVG-UPM

¿How to build intelligent machines?

Explicit model− top-down methodology

Example learning− boton-up methodology

- paradigms: physical equations expert systems

- paradigms: experimental parameters neural networks

Self-learning

Parallel processing

Distributed Patterns

Signal processing

Programmed

Serial Processing

Symbolic data

High dimensional statespace searching

Learning based systemsKnwoledge based systems

CVG-UPMC

Ojectives of the subject

Find a model that predicts the right output to anew input, considering outputs to previous inputs.

CVG-UPM

Learning applications

Pattern Recognition

Control

Identification

Associative memory

Optimization

CVG-UPMC

Pattern Reconition Applications

Representation, recognition and predictionof the state of a multidimensional inputvector, which can be:- The state of an industrial process from the field

sensors (includes also alarm management)- The state of an electrical net- The atmospheric state from a spread net of sensors- The seismical or geological state- The state of a vehicle (e.g. airplane, car, …)- The commercial situation of a company from its whole

accountability- Patterns in images (e.g. visual, IR, electromagnetic, ..)

CVG-UPM

Computer Vision applications

Abnormalcristalitation

preprocessing segmentation feature extraction Recognition

CVG-UPMC

Your applications

1. Synthetic data

2. Real data

CVG-UPM

Homeworks in Moodle:Files/Exercises

CVG-UPMC

Exercise 1.1

Print the 2 different handwritten images of thesame number for 4 different numbers

1.- Intelligence & Learning - UPM · CVG-UPM COMPUTER VISION P. Campoy Machine Learning and Neural...

Documents

Transcript of 1.- Intelligence & Learning - UPM · CVG-UPM COMPUTER VISION P. Campoy Machine Learning and Neural...

Mmap 4 teaching and Learning @ CADEe UPM

UPM – the biofore company · | © UPM Value creation through sustainable growth and cash generation 7 UPM Biorefining UPM Raflatac UPM Specialty Papers UPM Plywood Sales 2016 UPM

RobustFill: Neural Program Learning under Noisy I/O · RobustFill: Neural Program Learning under Noisy I/O ... est problems in machine learning and artiﬁcial intelligence ... Neural

Artiﬁcial Neural Networks Connectionist Learning Machinesci.louisville.edu/kerem/evraklar/sunum/CECS694_01_seminar.pdfArtiﬁcial Neural Networks Connectionist Learning Machines

Perceptrons and Learning Learning in Neural Networks.

Neural Networks and Deep Learning - CSE - IIT Kanpur€¦ · Neural Networks and Deep Learning . Example Learning Problem . Example Learning Problem ... –Radial basis functions

Deep Learning in Neural Networks: An Overviejuergen/DeepLearning28May2014.pdf · Deep Learning in Neural Networks: An Overview ... 1 Introduction to Deep Learning ... Neural Fitted

Biologically plausible learning in recurrent neural …...2016/09/29 · Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive

Pattern Recognition (PR) Neural Networks (NN) - OCW …ocw.upm.es/ciencia-de-la-computacion-e-inteligencia-artificial/... · CVG-UPM COMPUTER VISION P. Campoy Neural Networks and

Chapter 10: Neural basis of learning Learning activity ...

Neural Optimizer Search with Reinforcement Learning - … · Neural Optimizer Search with Reinforcement Learning ... Neural Optimizer Search with Reinforcement Learning ... Our approach

Deep Learning: Feedforward Neural Nets and Convolutional ... · PDF fileDeep Learning: Feedforward Neural Nets and Convolutional Neural Nets Piyush Rai Machine Learning (CS771A) Nov

Convolutional neural networks for image classificationceur-ws.org/Vol-2546/paper06.pdf · Keywords: machine learning, deep learning, neural network, recognition, convolutional neural

Machine Learning and Neural Networks - UPM€¦ · · 2015-05-271 CVG-UPM COMPUTER VISION P. Campoy Neural Networks and Pattern Recognition? by? Machine Learning and Neural Networks

7 Neural Networks Learning

Métodos Actuales de Machine Learning Neural Networksdc.exa.unrc.edu.ar/rio2016/sites/default/files/Neural Networks... · Métodos Actuales de Machine Learning Neural Networks

Supervised learning neural networks Multilayer perceptron ...liacs.leidenuniv.nl/~nijssensgr/CI/2011/5 neural networks...Supervised learning neural networks • Multilayer perceptron

Archivo Digital UPM - Archivo Digital UPM

E-LEARNING IN UPM · E-LEARNING IN UPM by : Centre for Academic Development (CADe) THE ROLE OF LECTURES IN CONDUCTING VIRTUAL CLASS 1. Design teaching delivery using the appropriate

Neural network retuning and neural predictors of learning ...Neural network retuning and neural predictors of learning success associated with cello training Indiana Wollmana,b,c,1,