Ce diaporama a bien été signalé.
Nous utilisons votre profil LinkedIn et vos données d’activité pour vous proposer des publicités personnalisées et pertinentes. Vous pouvez changer vos préférences de publicités à tout moment.

Le Machine Learning de A à Z

1 593 vues

Publié le

Le Machine Learning, l’IA, le DeepLearning, les Statistiques, le Data Mining… bref, tous ces mots sont les buzz words du moment mais que se cache-t-il derrière ?
A travers des exemples concrets, on parcourra les différentes approches du Machine Learning, les grandes familles d’algorithmes (n’ayez crainte : sans rentrer dans le cœur de leurs implémentations), puis les outils et les frameworks à la disposition des Data Scientists… et pour finir, on essayera de prédire l’avenir !

Salon Data - Nantes - 19 Septembre 2017
https://salondata.fr/2017/07/12/0930-1030-ml/

Publié dans : Données & analyses

Le Machine Learning de A à Z

  1. 1. Machine Learning de A à Z NANTES DIGITAL WEEK 19 Septembre 2017
  2. 2. Alexia Audevart Data & Enthusiasm @aaudevart Présidente meet-up Toulouse Data Science Co-organisatrice du devfest Toulouse
  3. 3. Definitions Machine Learning Approaches Machine Learning Methods Machine Learning Trends Machine Learning Tools and Frameworks 1 2 3 4 5 Machine Learning Summary
  4. 4. Types of Data WHAT IS A DATA? • Datum : an item of factual information derived from measurement or research • Data : a collection of facts from which conclusions may be drawn (plural of Datum) 1 Structured Data Semi Structured Data Unstructured Data LOG
  5. 5. Data Mining DataBase Artificial Intelligence Machine Learning Statistic Pattern Recognition DATA BUZZ WORDS 1 Deep Learning
  6. 6. MACHINE LEARNING 1 Experience Task Performance Input Data • Housing Prices • Images • Customer Transactions • Clickstream data Task • Predict Prices • Categorize images • Segment customers • Optimize user flows Performance • Accurate Prices • Correctly sorted images • Coherent groupings • KPI lifts
  7. 7. MACHINE LEARNING A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E. 1 Tom Mitchell – 1998 Experience Task Performance
  8. 8. QUIZZ 1 Suppose your email program watches which emails you do or do not mark as spam, and based on that learns how to better filter spam. Identify the task T, the performance measure P and the experience E • Classifying emails as spam or not spam. • Watching you label emails as spam or not spam. • The number (or fraction) of emails correctly classified as spam/not spam.
  9. 9. MACHINE LEARNING : WHEN ? Human expertise does not exist Humans are unable to explain their expertise Navigating on Mars Solution changes in time Solution needs to be adapted to particular cases Navigating on Mars Speech Recognition Routing on a computer network User Biometrics 1
  10. 10. WHAT IS A FEATURE ? Features are elements or dimensions of your dataset. 1
  11. 11. WHAT IS A MODEL ? Definition : a mathematical representation of relationships in a dataset. 1
  12. 12. MACHINE LEARNING ALGORITHMS • Learning Algorithm : infer the model parameters from the data • Inference Algorithm : infer prediction from a model 1
  13. 13. Definitions Machine Learning Approaches Machine Learning Methods Machine Learning Trends Machine Learning Tools and Frameworks 1 2 3 4 5 Machine Learning Summary
  14. 14. SUPERVISED LEARNING DEFINITION • The correct class of the training data are known. • All data are labeled • The algorithm learn to predict the output from the input data. TWO MAIN GOALS : 2 Predictive Informative Make prediction for a new sample described by its attributes Help to understand the relationship between the inputs and the output.
  15. 15. SUPERVISED LEARNING 2 # Bedrooms = A Size = B Zip code = C … Price = Y 3 2104 31500 400 000 3 1600 87220 330 000 3 2400 45760 369 000 … … 4 3000 76540 540 000 INPUTS OUTPUT Feature A 𝑌" = ℎ(𝐴, 𝐵, 𝐶, … . ) Model Hypothesis Supervised Learning Goal: Minimize error between Y et 𝑌" Labeled Dataset
  16. 16. New Input Data Training Input Data 2 Expected Label Text, Documents, Images, Sounds, …. MODELS Text, Documents, Images, Sounds, …. Machine Learning Algorithm Labels SUPERVISED LEARNING Features Vectors Features Vector
  17. 17. Classification problem • Predict class from observations • Symbolic output SUPERVISED LEARNING 2 Regression problem • Predict value from observations • Numerical output
  18. 18. SUPERVISED LEARNING - EXAMPLES Spam Email Detection Biomedical domain : differentiation of diseases Speech recognition Time series prediction Handwritten character recognition Object recognition in computer vision prediction electricity load, network usage, stock market prices 2
  19. 19. UNSUPERVISED LEARNING DEFINITION • The correct class of the training data are NOT known. • All data is unlabeled • The algorithms learn to inherent structure from the input data. Unsupervised learning problems can be further grouped into : 2 Clustering Association Dimension reduction Anomaly Detection
  20. 20. New Input Data Training Input Data 2 Likelihood or Cluster ID Or Better Representation Text, Documents, Images, Sounds, …. MODELS Text, Documents, Images, Sounds, …. Machine Learning Algorithm Features Vectors UNSUPERVISED LEARNING Features Vector
  21. 21. UNSUPERVISED LEARNING - EXAMPLES Customer Segmentation Face Image Recognition Recommendation system 2
  22. 22. REINFORCEMENT LEARNING Principles: • Close to human learning • Algorithm learns a policy of how to act in a given environment • Every Action has some impact in the environment, and the environment provides rewards that guides the learning algorithm Goal: • Maximize the expected sum of future rewards 2 Environment: • Stochastic (Tetris) • Adversarial (Chess) • Partially unknown (Bicycle) • Partially observable (Robot)
  23. 23. Robotics AlphaGoGame Playing REINFORCEMENT LEARNING EXAMPLES 2
  24. 24. SEMI-SUPERVISED LEARNING • Learning from both labeled and unlabeled data • Using a mixture of supervised and unsupervised techniques 2
  25. 25. Definitions Machine Learning Approaches Machine Learning Methods Machine Learning Trends Machine Learning Tools and Frameworks 1 2 3 4 5 Machine Learning Summary
  26. 26. MACHINE LEARNING ALGORITHMS 3 Source Image : Blog Olivia Klose
  27. 27. MACHINE LEARNING ITERATIVE PROCESS 3 Historical Data Compare Models Feature Engineering Test Train Validation Validation Results Hyper-parameter tuning Build Models MODELS Test Results
  28. 28. MACHINE LEARNING ALGORITHM3
  29. 29. Definitions Machine Learning Approaches Machine Learning Methods Machine Learning Trends Machine Learning Tools and Frameworks 1 2 3 4 5 Machine Learning Summary
  30. 30. Decisions tree 4 SYMBOLISTS Addition 1 + 1 ? Substraction 1 + ? = 2 Deduction Socrates is Human + Humans are mortal ? Induction Socrates is Human + ? = Socrates is Mortal Origins Logic, Philosophy _______________________ Master Algorithms Inverse Deduction _______________________ Problems Knowledge Composition
  31. 31. BAYESIANS Statistics Bayesians Origins Statistics _____________________________ Master Algorithms Probabilistic Inference _____________________________ Problems Uncertainty 4
  32. 32. CONNECTIONISTS A neuronOrigins Neuroscience _____________________________ Master Algorithms Backpropagation _____________________________ Problems Credit Assignment An artificial neuron 4
  33. 33. EVOLUTIONARIES Genetic Algorithms Applying the idea of genomes and DNA in the evolutionary process to data Origins Evolutionary biology _____________________________ Master Algorithms Genetic Programming _____________________________ Problems Structure Discovery 4
  34. 34. ANALOGIZERS Nearest NeighborOrigins Psychology _____________________________ Master Algorithms Kernel Machines (SVM : Support Vector Machines) _____________________________ Problems Similarities 4
  35. 35. EvolutionariesConnectionistsBayesiansSymbolists THE 5 TRIBES OF MACHINE LEARNING Systematically reduce uncertainty Simulate evolutionEmulate the brain Fill the gaps in existing knowledge Source Image : Blog PWC Pedro Domingo-The Master Algorithm 4 Analogizers Notice similarities between old and new Each tribe represents a different school of thought within the machine learning space. They are often combined to attack problems from different angles.
  36. 36. Definitions Machine Learning Approaches Machine Learning Methods Machine Learning Trends Machine Learning Tools and Frameworks 1 2 3 4 5 Machine Learning Summary
  37. 37. MACHINE LEARNING 5 Python R Matlab Octave
  38. 38. Dataiku Knime RapidMiner SAS ML PLATFORMS 5
  39. 39. Amazon Machine Learning Azure Machine Learning Studio Big ML Google Machine Learning ML IN THE CLOUD 5
  40. 40. Mahout Spark Machine Learning H20 SCALABLE MACHINE LEARNING 5
  41. 41. DEEP LEARNING 5 Caffe CNTK TensorFlow Theano MXNet Torch Apache Singa
  42. 42. What’s next ? Most of the knowledge in the world in the future is going to be extracted by machines and will reside in machines Yann LeCun – Director of AI Research, Facebook

×