Intelligent sensor and learning challenges for context aware appliances >> Stéphane Canu



Yüklə 445 b.
tarix27.10.2017
ölçüsü445 b.


Intelligent sensor and learning challenges for context aware appliances

  • >> Stéphane Canu

  • scanu@insa-rouen.fr

  • asi.insa-rouen.fr/~scanu

  • INSA Rouen, France - EU

  • Laboratoire PSI


1984: La souris et leMacintoch



La technologie d'aujourd'hui

  • Loi de Moore

  • Communication "sans fil"

  • L'ère des données



Wearable



IHM



Wearable



Reasearch on wearable



Wearable



context aware appliances



General Motors and CMU



Oops! Where is my car?

  • Old fashion software design: process

        • Match the sentence
        • Send the query to the satellite
        • Satellite send query to the car on its own frequency
        • Car answers…
    • Tell the computer what to do (where is the switch)
  • Distributed software design: interaction

    • Software agents talk together
  • Future way: Programming by Example

    • Show the computer what to do
  • Today's solution: Louis my 3 years old son



Calm technology

  • Ubiquitous computing

    • One people - many computer
  • Technology at our service

    • Reactive to what user do
    • Proactive - Prepare what to do next
    • Situated – sharing context
    • (Hans Gellersen, Sensing in Ubiquitous Computing)
  • Adapted to our needs

    • New functionalities and new behaviors
    • New way of communicating
    • Learn to adapt


What is the context?

  • user

    • activity (available/meeting)
    • location,
    • identity, profile
  • environment monitoring

    • time, day/night, temperature, weather,
    • resources (networks, services…)
  • appliance - proprioception

    • usage - functionalities
    • maintenance
    • resources (energy…)


Sensing context from the environment presentation roadmap



Context from data

  • Unbelievable capacity

    • Moore’s law
  • New sensors

    • Artificial nose
    • Bio sensor
  • “Personal” data

    • humor: affective computing


Biological sensors





Too much information kills information

  • Critic of the "Data Era"

  • Data smog

  • Non measurable things

  • Ethical consequences

    • the Orwellian future


Intelligent sensors

  • Requirements:

    • Data
    • Accuracy and confidence
    • Self diagnostic
    • Self calibration
  • How to do it?

    • Uncertainty management
    • Learning ability
    • Adaptation ability
    • Fault detection mechanism


Data validation

  • Mono sensor validation

    • Static validation
      • Mean, variance
    • Dynamic validation
      • Cusum (control charts)
      • Trend analysis
  • Multisensor validation

    • Residual analysis
    • Fusion: Joint probability estimation
    • Prior knowledge: Balanced relations
  • Hierarchical validation

    • Multisensor perception


Software sensor

  • Value + confidence interval + validity domain

  • How to build it ?

    • From a model: tracking = Kalman filter
    • When no model is available: learn it!


Towards proprioceptors

  • Learn

  • How to learn?

    • Gaussian mixture + EM
    • Include prior: Bayesian networks
    • Deal with uncertainty: Evidence framework
  • Use to:

    • Detect non nominal situations
    • Replace missing data


What is data?

  • Individuals or measurements

  • Associated variables

  • Data set (matrix)

    • line = measurements
    • column = variable
  • Data: point clouds

    • Data exploration: recognize patterns


Summarize data

  • Non linear components analysis

    • Feature space: kernel (PCA or ICA)
    • Local linear
    • Quantisation (SOM)
    • Relevant distance
  • Select features

    • Local adapted representation
    • Feature selection
  • Select relevant situations

    • Sparse learning
    • Kernel learning


Kernel representation Distance maps



Example of kernel map



Looking for hiden shapes

  • Data point = information + noise

  • Principal curve

    • Non linear PCA
  • Independent curve

    • Non linear ICA




Information retrieval

  • What for

    • User profiling
    • User identification
    • Battery discharge rate
    • Sequence induction…
  • Classification problem



A brief historical perspective of machine learning

  • Before machines

    • Statistics: PCA, DA, regression, CART, kNN
  • 70's - Learning is logic

    • Grammatical inference in expert systems
  • 80's - Learning is human

    • Neural networks: backprop
  • 90's - Learning is a problem: COLT

    • Kernel machines: SVM
    • Mixture of experts: adaboost


What is learning?

  • Data

    • Training set
    • Test point looking for such that
  • Learning is balancing

    • Hypothesis set (Neural networks, Kernels)
    • Fitting criterion (least square, absolute value)
    • Compression criterion (penalization, Margin)
    • Balancing mechanism (cross validation, generalization)


Linear discrimination separable case



Linear discrimination separable case



The classifier Margin



Maximize the margin Be sparse



What is learning?



Summarize Input adaptive scaling

  • Enumerate all combination

    • …and score
  • Preprocessing

    • Information theory
    • Statistical test
  • Wrapper

    • Use a relevance index
    • Learn and select together


Summarize patterns



Learning machines challenges

  • Hypothesis set

  • Fitting criterion

    • Sparse distance criterion
    • Select relevant input (adaptive scaling)
    • Relevant distance: adapt the kernel
  • Compression criterion

    • Information issues
    • Global optimization
  • Balancing mechanism

    • Efficient direct algorithm (one shot learning)


Context assessment

  • Deal with uncertainty

    • plausibility / credibility
    • unknown states / ability to evolve
    • data fusion: evidence theory
  • Take into account prior knowledge: transitions

    • temporal representation
    • uncertain transitions
    • learn probabilities or possibilities
  • Learn the model

    • don't start from scratch
    • create and delete contexts
  • Adapt context determination to user

    • from a global imprecise context to specific context


Context implementation

  • Context = state

  • State = stochastic

    • Markov model
    • Bayesian networks
  • Identify = decision theory (data fusion)

    • Information retrieval
  • Learn context

    • Knowledge discovery
    • Create / delete
    • Context hierarchy (time granularity)


New idea to deal with context

  • Current context: working memory

    • Prior knowledge: transition law
  • Available information: evidence

    • Data fusion
  • Learn context

    • Transition law
    • Context retrieval from data
  • Context is a language

  • Speech recognition

    • Markovian model
    • Evidence
    • Language + previous state
    • Locator's adaptation


Context: Research chalenges

  • Inputs

    • Deal with uncertainty (and missing data)
    • Representation
    • Data fusion (multimedia fusion)
  • Context

    • Define a language
    • Represent previous state
    • Learn transition
  • Feed Back to inputs

  • Adapt transition to the user

    • Loop the user: reinforcement
    • Control mechanism (stability/plasticity dilemma)


Break through

  • What is information?

    • Computer science
    • Coding
    • Signal
  • Mathematics

    • Statistics & computer science
    • Pattern recognition
    • Functional analysis
    • ??????


My long bet



Research challenges

  • create context

    • how to define prior contexts: user’s needs
    • how to represent contexts: stochastic automaton
    • learn from data: modify, create and destroy context
  • decide context

    • validate data software sensors
    • select relevant inputs representation + distance
    • select relevant patterns wavelets
    • select relevant situations SVM and kernel
    • make decision using data fusion Dempster-Shafer + EM
  • loop with the user

    • reinforcement learning
    • user’s needs


Questions?

  • Asia

    • Scurry™, Wearable & Virtual Keyboard - Samsung,
    • K. Doya for reinforcement
  • America

    • Context Aware Computing group - Media lab MIT
    • CMU, Stanford
    • Georgia tech: Future Computing Environments
    • Smart Matter Integrated Systems (Xerox PARC)
    • Montreal – learning lab
  • Australia

  • Europe

    • Telecooperation Office (TecO) at the University of Karlsruhe
    • The disappearing computer, a EU-funded proactive initiative
    • The Smart-Its project
    • Equator project focuses on the integration of physical and digital interaction
    • Perceptual Computing in general and Computer Vision in ETH Zurich
    • IDIAP for machine learning and speech recognition
    • PSI, France for learning




From macroscopic…





Emotion detection >> E-Motions



Learning accuracy

  • Find (a,b) such that

  • Model the model

    • The sandwich estimator, (Tibshirani, 1996)
      • Likelihood Based on the Hessian matrix
    • Confidence machine (Gammerman RHC, 1999)
      • Confidence: 73.11% - Credibility: 51.37%
  • Sample the models

    • Bootstrap (Heskes 1997)
  • Learn the error

    • Train using absolute error




Movie synthesis from text



From one expression to another



Non euclidian metrics



Hyperbolic Self-Organizing Map



Example on movies - HSOM



Example on movies



Curvlets



Curvlets



Select relevant situations

  • Relevant representation

    • "Invent" features
    • Select features
  • Relevant "distance"

    • map
    • Use kernel
  • Summarize the examples

    • Define a relevant global criterion to be minimized
    • Support vector machines (SVM)


Learning architecture

  • Agent - Data base - Communication

  • Metadata

  • Context language

  • Adaptability: control mechanism

  • Pre programming: anticipation

  • Open – modular – distributed

    • The Ektara Architecture (MIT for wearable)
    • Nexus - A Platform for Context-Aware Systems
    • The Context-Toolkit (Geargia Tech)


Future appliances?

  • Deal with the context

    • Recognize
    • Adapt
    • Create
  • Inference, Learning, discovery,

    • Represent
    • Decide
    • Deal with time
  • From user interface to user interaction

    • Reinforcement learning
    • Human factors
  • How to know what we need?



Kataloq: ~scanu
~scanu -> Dea perception et Traitement de l’Information Reconnaissance des formes
~scanu -> Réseaux de neurones artificiels «programmation par l’exemple» S. Canu, laboratoire psi, insa de Rouen
~scanu -> S. Canu, Ph. Leray, A. Rakotomamonjy laboratoire psi
~scanu -> Algorithmes d’apprentissage rapide pour les réseaux neuronaux multi-couches
~scanu -> Réseaux de neurones artificiels «le neurone formel» S. Canu, laboratoire psi, insa de Rouen
~scanu -> Outils d’analyse statistiques «programmation par l’exemple» S. Canu, laboratoire psi, insa de Rouen
~scanu -> Réseaux de neurones artificiels «la rétropropagation du gradient» S. Canu, laboratoire psi, insa de Rouen
~scanu -> Road map linear discrimination: the separable case
~scanu -> Dea perception et Traitement de l’Information Reconnaissance des formes
~scanu -> Khoufi Héla,Poinsignon Jean-Marc dea icsv tp1: étude bibliographique

Yüklə 445 b.

Dostları ilə paylaş:




Verilənlər bazası müəlliflik hüququ ilə müdafiə olunur ©muhaz.org 2020
rəhbərliyinə müraciət

    Ana səhifə