Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Deep Water - Bringing Tensorflow, Caffe, Mxnet to H2O


Published on

Arno Candel introduces Deep Water, which brings Tensorflow, Caffe, Mxnet to H2O. It also brings support for GPUs, image classification, NLP and much more to H2O.

- Powered by the open source machine learning software Contributors welcome at:
- To view videos on H2O open source machine learning software, go to:

Published in: Data & Analytics

Deep Water - Bringing Tensorflow, Caffe, Mxnet to H2O

  1. 1. Deep Water Or: Bringing TensorFlow et al. to H2O Arno Candel, PhD Chief Architect, Physicist & Hacker, @ArnoCandel July 18 2016
  2. 2. Overview Machine Learning (ML) Artificial Intelligence (A.I.) Computer Science (CS) Deep Learning (DL) hot hot hot hot hot
  3. 3. A Simple Deep Learning Model: Artificial Neural Network heartbeat blood pressure oxygen send to regular care send to intensive
 care unit (ICU) IN: data OUT: prediction nodes : neuron activations (real numbers) — represent features arrows : connecting weights (real numbers) — learned during training : non-linearity x -> f(x) — adds model complexity from 1970s, now rebranded as DL
  4. 4. • conceptually simple • non linear • highly flexible and configurable • learned features can be extracted • can be fine-tuned with more data • efficient for multi-class problems • world-class at pattern recognition Deep Learning Pros and Cons Pros: • hard to interpret • theory not well understood • slow to train and score • overfits, needs regularization • many hyper-parameters • inefficient for categorical variables • very data hungry, learns slowly Cons: Deep Learning got boosted recently by faster computers
  5. 5. Brief History of A.I., ML and DL John McCarthy
 Princeton, Bell Labs, Dartmouth, later: MIT, Stanford 1955: “A proposal for the Dartmouth summer research project on Artificial Intelligence” with Marvin Minsky (MIT), Claude Shannon 
 (Bell Labs) and Nathaniel Rochester (IBM) A step back: A.I. was coined over 60 years ago
  6. 6. 1955 proposal for the Dartmouth summer research project on A.I. “We propose that a 2-month, 10-man study of artificial intelligence be carried out during the summer of 1956 at Dartmouth College in Hanover, New Hampshire. The study is to proceed on the basis of the conjecture that every aspect of learning and any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it. An attempt will be made to find how to make machines use language, form abstractions and concepts, solve kinds of problems now reserved for humans, and improve themselves. We think that a significant advance can be made in one or more of these problems if a carefully selected group of scientists work on it together for one summer.”
  7. 7. Step 1: Great Algorithms + Fast Computers 1997: Playing Chess (IBM Deep Blue beats Kasparov) Computer Science
 30 custom CPUs, 60 billion moves in 3 mins “No computer will ever beat me at playing chess.”
  8. 8. Step 2: More Data + Real-Time Processing 2005: Self-driving Cars
 DARPA Grand Challenge, 132 miles (won by Stanford A.I. lab*) Sensors & Computer Science
 video, radar, laser, GPS, 7 Pentium computers “No computer will ever drive a car!?” *A.I. lab was established by McCarthy et al. in the early 60s
  9. 9. Step 3: Big Data + In-Memory Clusters 2011: Jeopardy (IBM Watson) In-Memory Analytics/ML 4 TB of data (incl. wikipedia), 90 servers,
 16 TB RAM, Hadoop, 6 million logic rules Note: IBM Watson received the question in electronic written form, and was often able to press the answer button faster than the competing humans. “No computer will ever answer random questions!?”
  10. 10. “No computer will ever understand my language!?” 2014: Google
 (acquired Quest Visual) Deep Learning
 Convolutional and Recurrent Neural Networks, with training data from users Step 4: Deep Learning • Translate between 103 languages by typing • Instant camera translation: Use your camera to translate text instantly in 29 languages • Camera Mode: Take pictures of text for higher-quality translations in 37 languages • Conversation Mode: Two-way instant speech translation in 32 languages • Handwriting: Draw characters instead of using the keyboard in 93 languages
  11. 11. Step 5: Augmented Deep Learning 2014: Atari Games (DeepMind) 2016: AlphaGo (Google DeepMind) Deep Learning
 + reinforcement learning, tree search,
 Monte Carlo, GPUs, playing against itself, … Go board has approx. 200,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000, 000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000 (2E170) possible positions. trained from raw pixel values, no human rules “No computer will ever beat the best Go master!?”
  12. 12. Microsoft had won the Visual Recognition challenge: Step 6: A.I. Chatbots have Opinions too!
  13. 13. What Will Change? Today Tomorrow Better Data — Better Models — Better Results Example: Fraud Prediction
  14. 14. What about Jobs? Anything that can be automated will be automated. Jobs of the past: assembly line work, teller (ATMs), taxi-firm receptionist Jobs being automated away now: resume matching, driving, language translation, education Jobs being automated away soon: healthcare, arts & crafts, entertainment, design, decoration, software engineering, politics, management, professional gaming, financial planning, auditing, real estate agent Jobs of the future: professional sports, food & wine reviewer
  15. 15. Maybe we’ll finally get the eating machine? 1936 Modern Times (Charlie Chaplin)
  16. 16. Live H2O Deep Learning Demo: Predict Airplane Delays 10 nodes: all
 320 cores busy real-time, interactive model inspection in Flow 116M rows, 6GB CSV file
 800+ predictors (numeric + categorical) model trained in <1 min:
 2M+ samples/second Deep Learning Model
  17. 17. H2O Elastic Net (GLM): 10 secs alpha=0.5, lambda=1.379e-4 (auto) H2O Deep Learning: 45 secs 4 hidden ReLU layers of 20 neurons, 1 epoch Features have non- linear impact Chicago, Atlanta, Dallas:
 often delayed Significant Performance Gains with Deep Learning Predict departure delay (Y/N) on 20 years of airline flight data (116M rows, 12 cols, categorical + numerical data with missing values) WATCH NOW AUC: 0.656 AUC: 0.703 (higher is better, ranges from 0.5 to 1) Feature importances 10 nodes: Dual E5-2650 (8 cores, 2.6GHz), 10GbE
  18. 18. READ MORE Kaggle challenge 2nd place winner
 Colin Priest READ MORE “For my final competition submission I used an ensemble of models, including 3 deep learning models built with R and h2o.” “I did really like H2O’s deep learning implementation in R, though - the interface was great, the back end extremely easy to understand, and it was scalable and flexible. Definitely a tool I’ll be going back to.” H2O Deep Learning Community Quotes
  19. 19. H2O Deep Learning Community Quotes READ MORE WATCH NOW “H2O Deep Learning models outperform other Gleason predicting models.” READ MORE “… combine ADAM and Apache Spark with H2O’s deep learning capabilities to predict an individual’s population group based on his or her genomic data. Our results demonstrate that we can predict these very well, with more than 99% accuracy.”
  20. 20. H2O Deep Learning Community Quotes
  21. 21. H2O Booklets DOWNLOAD R Python Deep Learning GLMGBMSparkling Water
  22. 22. KDNuggets Poll about Deep Learning Tools & Platforms H2O and TensorFlow are tied usage of Deep Learning tools in past year
  23. 23. TensorFlow + H2O + Apache Spark = Anything is possible water/blob/master/py/examples/ notebooks/TensorFlowDeepLearning.ipynb
  24. 24. Integration with existing GPU backends Leverage open-source tools and research for TensorFlow, Caffe, mxnet, Theano, etc. Scalability and Ease of Use/Deployment of H2O Distributed training, real-time model inspection Flow, R, Python, Spark/Scala, Java, REST, POJO, Steam Convolutional Neural Networks Image, video, speech recognition, etc. Recurrent Neural Networks Sequences, time series, etc. NLP: natural language processing Hybrid Neural Networks Architectures Speech to text translation, image captioning, scene parsing, etc. Deep Water: Next-Gen Deep Learning in H2O Enterprise Deep Learning for Business Transformation
  25. 25. Deep Water: Next-Gen Deep Learning in H2O Don’t miss our Deep Learning sessions tomorrow afternoon! TensorFlow mxnetCaffe H2O