Machine Learning 101 - CUTI & Tryolabs

Machine Learning 101 meetup presentation. Date: 10/20/2016.

Presented by Martín Alcalá Rubí and Alan Descoins from Tryolabs.

Transcript

3. "Software is eating the world" 3
4. 4 "AI is the new electricity"
6. Machine Learning 101 An introduction for developers 6
7. Agenda 1. What is Machine Learning 2. In practice: Python & its benefits 3. Types of Machine Learning problems 4. Steps needed to solve them 5. How two classification algorithms work a. K-Nearest Neighbors b. Support Vector Machines 6. Evaluating an algorithm a. Overfitting 7. Demo 8. (Very) basic intro to Deep Learning & what follows 7
8. What is Machine Learning? The subfield of computer science that "gives computers the ability to learn without being explicitly programmed" (Arthur Samuel, 1959). A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E” (Tom Mitchell, 1997) • Machine Learning vs AI? 8
9. 9 Some Python code
10. Why Python? • Simple & powerful • Fast prototyping ◦ Batteries included • Lots of libraries ◦ For everything, not just Machine Learning ◦ Bindings to integrate with other languages • Community ◦ Very active scientific community ◦ Used in academia & industry 10
11. Data Science “Swiss army knife” Data preparation / exploration / visualization • Pandas • Matplotlib • Seaborn • Orange Modeling / Machine Learning • Scikit-learn • mllib (Apache Spark) Text focused • Gensim • nltk Deep learning • Keras • TensorFlow, Theano 11
12. Types of ML problems Supervised • Learn through examples of which we know the desired output. • Two types: ◦ Classification (discrete variables, ie. spam/no spam) ◦ Regression (continuous output, ie. temperature) 12 Unsupervised • Discover latent relationships in the data • Two types: ◦ Dimensionality reduction (curse of dimensionality) ◦ Clustering Also have semi-supervised (use labeled and unlabeled data).
13. Steps in every Machine Learning problem To solve any ML task, need to go through: 1. Data gathering 2. Data processing & feature engineering 3. Algorithm & training 4. Applying model to make predictions (evaluate, improve) 13
14. Data gathering • Depends on the specific task • Might need to put humans to work :( ◦ Ie. Manual labelling for supervised learning ◦ Domain knowledge. Maybe even experts. ◦ Can leverage Mechanical Turk / CrowdFlower. • May come for free, or “sort of” ◦ Ie. Machine Translation. ◦ Categorized articles in Amazon, etc. • The more the better ◦ Some algorithms need large amounts of data to be useful (ie. neural networks). 14
15. Data processing Is there anything wrong with the data? • Missing values • Outliers • Bad encoding (for text) • Wrongly-labeled examples • Biased data ◦ Do I have many more samples of one class than the rest? Need to fix/remove data? 15
16. Feature engineering What is a feature? A feature is an individual measurable property of a phenomenon being observed Our inputs are represented by a set of features. Eg: • To classify spam email, features could be: ◦ Number of times some word appears (ie. pharmacy) ◦ Number of words that have been ch4ng3d like this. ◦ Language of the email (0=English, 1=Spanish, …) ◦ Number of emojis 16 Buy ch34p drugs from the ph4rm4cy now :) :) :) :) (1, 2, 0, 4) Feature engineering
17. Feature engineering (2) • Extract more information from existing data • Not adding “new” data per-se ◦ Making it more useful ◦ With good features, most algorithms can learn faster • It can be an art ◦ Requires thought and knowledge of the data Two steps: • Variable transformation (eg. dates into weekdays, normalizing) • Feature creation (eg. n-grams for texts, if word is capitalized to detect names, etc) 17
18. Algorithm & training Supervised • Linear classifier • Naive Bayes • Support Vector Machines (SVM) • Decision Tree • Random Forests • k-Nearest Neighbors • Neural Networks (Deep learning) Unsupervised / dimensionality reduction • PCA • t-SNE • k-means • DBSCAN They all understand vectors of numbers. Data are points in multi-dimensional space. 18
20. k-Nearest Neighbors (k-NN) Classification or regression. Idea (classification): • Choose a natural number k >= 1 (parameter of the algorithm) • Given the sample X we want to label: ◦ Calculate some distance (ie. euclidean) to all the samples in the training set. ◦ Keep the k samples with the shortest distance to X. These are the nearest neighbors. ◦ Assign to X whatever class the majority of the neighbors have. 20
21. 21 K = 1 K = 5
22. k-Nearest Neighbors (k-NN) (2) • Fast computation of nearest neighbors is an active area of research. • Naive brute-force approach computes distance to all points, need to keep entire dataset in memory at classification time (no offline training). • Need to experiment to get the right k. There are other algorithms that use approximations to deal with these inefficiencies. 22
24. Support Vector Machines (SVM) Idea: • Separate data linearly in space. • There are infinite planes that can separate blue & red dots. • SVM finds the optimal hyperplane to separate the two classes (the one that leaves the most margin). 24
25. Support Vector Machines (SVM) (2) • SVMs focus only on the points that are the most difficult to tell apart (other classifiers pay attention to all the points). • We call them the support vectors. • Decision boundary doesn’t change if we add more samples that are outside the margin. • Can achieve good accuracy with fewer training samples compared to other algorithms. Only works if data is linearly separable. • If not, can use a kernel to transform it to a higher dimension. 25
26. Support Vector Machines: Kernel Trick 26
27. Evaluating • Split train / test set. Should not overlap! • Accuracy ◦ What % of samples did it get right? • Precision / Recall ◦ True Positives, True Negatives, False Positives, False Negatives ◦ Precision = TP / (TP + FP) (out of all the classifier labeled positive, % that actually was) ◦ Recall = TP / (TP + FN) (out of all the positive, how many did it get right?) ◦ F-measure (harmonic mean, 2 * Precision * Recall / (Precision + Recall)) • Confusion matrix • Many others 27
28. Evaluating a spam classifier: example 28 Id Is spam Predicted spam 1 Yes No 2 Yes Yes 3 No Yes 4 Yes Yes 5 No No 6 Yes No 7 No No accuracy = 4/7 ~ 0.57 precision = 2/(2 + 1) = ⅔ ~ 0.667 recall = 2/(2 + 2) = ½ ~ 0.5 F-measure = 2*(2/3 * 1/2)/(2/3 + 1/2) = 4/7 ~ 0.57 Confusion matrix Predicted spam Predicted not spam Spam 2 (TP) 2 (FN) Not spam 1 (FP) 2 (TN)
29. Overfitting • Models that adjust very well (“too well”) to the training data • It does not generalize to new data. This is a problem! 29
30. Preventing overfitting • Detect outliers in the data • Simple is better than complex ◦ Fewer parameters to tune can bring better performance. ◦ Eliminate degrees of freedom. Eg. polynomial. ◦ Regularization (penalize complexity). • K-fold cross validation (different train/test partitions) • Get more training data! 30
31. Demo: scikit-learn 31
32. What is Deep learning? • In part, it is rebranding of old technology. • First model of Artificial Neural Networks was proposed in 1943 (!). • The analogy to the human brain has been greatly exaggerated. 32
33. Deep learning • Training deep networks in practice was only made possible by recent advances. • Many state of the art breakthroughs in recent years (2012+), powered by the same underlying model. • Some tasks can now be performed at human accuracy (or even above!). 33
34. Deep learning 34 Raw input Manual feature extraction Algorithm Output • These algorithms are very good at difficult tasks, like pattern recognition. • They generalize when given sufficient training examples. • They learn representations of the data. Raw input Deep Learning algorithm Output Traditional ML Deep Learning
35. Deep learning is already in your life 35
36. Deep learning is good with images 36
37. Deep learning games and art? 37
38. Deep learning on the road 38
39. What follows There is A LOT to learn! Many active research areas and infinite applications. We are living a revolution. • Rapid progress, need to keep up ;) • Entry barrier for using these technologies is lower than ever. • Processing power keeps increasing, models keep getting better. • What is the limit? 39
40. Stay tuned. Thank you :) @tryolabs 40