Big Data and Machine Learning

Presentation given to the BCS Advanced Computing SIG in February 2017

Transcript

3. Three V`s of Big Data
4. Data volumes by 2020
5. Big Data: Architectures
7. Hadoop vs Spark vs Storm !  All : O/S frameworks; real-time BI and BD analytics; implemented in JVM based programming languages !  Hadoop : Batch processing; latency in minutes; Map-Reduced jobs used for programming !  Spark : Batch, Graph and ML; latency few seconds; programmed in Scala/Java !  Storm : Only streaming; latency sub-seconds; own Java-API
9. Data Science is confusing!
12. The usual “suspects” !  Matlab : ( Octave ) !  R !  Python !  JVM : ( Java / Scala / Clojure ) !  SAS / SPSS !  Excel !  Julia
13. Which programming language? !  V1.0 as released in 1991 !  Does not have native arrays !  The latest version is not 100% compatible with the previous one !  Is 30-50 times slower than ‘C’ code !  Presently is the most popular language of choice among Data Scientists !  Currently is the best choice for studying machine learning.
14. The answer is … Python
16. Machine Learning? !  ML solves problems that cannot be solved by numerical means alone. !  Among the different types of ML tasks, a crucial distinction is drawn between supervised and unsupervised learning !  Supervised machine learning: The program is “trained” on a pre-defined set of “training examples”, which then facilitate its ability to reach an accurate conclusion when given new data. !  Unsupervised machine learning: The program is given a bunch of data and must find patterns and relationships within them
17. Supervised ML has several major subcategories !  Regression ML: Systems where the value being predicted falls somewhere on a continuous spectrum. These systems help us with questions of “How much?” or “How many?”. !  Classification ML: Systems where we seek a yes-or-no prediction, such as “Is this tumer cancerous?”, “Does this product meet specified quality standards?”, and so on. !  Bayesian ML: Systems where we have some prior insight and wish to use the data to establish better predictive models.
18. Classification Problems
19. Classification Concepts !  Cost Function: Used to measure how close the predicted values are to their corresponding real values. !  Decision Trees: Algorithms that can used for classification or regression predictive modeling problems (CART). !  Overfitting: Irrelevant attributes can result in overfitting the training example data. !  Underfitting: A model that can neither classify the training data nor generalize to new data.
20. Random Forests !  Random decision forests are an ensemble learning method for classification, regression and other tasks, that operate by constructing a multitude of decision trees at training time. !  They try to output the class that is the mode of the classes (classification) or mean prediction (regression) of the individual trees. !  Random decision forests are designed to correct for decision trees' habit of overfitting to their training set.
21. Sebastian Raschka
22. What do you need for ML in Python !  Anaconda (Python) !  Jupyter notebook IDE !  GIT !  Some “well-known” packages –  numpy, scipy –  pandas –  matplotlib –  scikit-learn –  seaborn
24. Some Useful URLS !  https://github.com/jdwittenauer/ipython-notebooks !  https://github.com/donnemartin/data-science-ipython-notebooks !  https://www.coursera.org/learn/python-machine-learning !  https://www.udemy.com/machinelearning/ !  https://www.datacamp.com/community/tutorials/machine-learning-python !  https://www.amazon.co.uk/Python-Machine-Learning-Sebastian-Raschka/ dp/1783555130 !  https://github.com/rasbt/python-machine-learning-book !  https://speakerdeck.com/rasbt/slides-from-machine-learning-with-scikit- learn-at-scipy-2016
25. Deep Learning !  Torch/PyTorch is a computational framework with an API written in Lua that supports machine-learning algorithms; used by large tech companies such as Facebook and Twitter !  Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation. !  TensorFlow™ is an open source software library for numerical computation using data flow graphs. A flexible architecture allows deployment computation to one or more CPUs or GPUs. !  Caffe is a well-known and widely used machine-vision library that ported Matlab’s implementation of fast convolutional nets to C and C++. !  MxNet is a machine-learning framework with APIs is languages such as R, Python and Julia which has been adopted by Amazon Web Services.
26. !  http://yann.lecun.com/exdb/mnist/ !  https://www.tensorflow.org/get_started/mnist/pros THE MNIST DATABASE of handwritten digits
27. And what about Julia? https://julialang.org/community/
28. JuliaML https://github.com/JuliaML
30. Final Thoughts !  ML approaches are computationally intense. !  General purpose and specific hardware is becoming increasingly more important. !  Distributed systems and/ parallelism is necessary to handle non-trivial problems. !  Networked systems based on Hadoop will not be sufficient in the future.
31. malcolm.sherrington@gmail.com h1ps://speakerdeck.com/sherrinmx