Small 20e3319227b03b50ec589c29a1e7fd25 400x400 Fabrizio Milo on

Tensorflow is one of the fastest growing open source deep learning frameworks available today. Tensorflow was developed internally by Google and released open source in November 2015.

Although it is mainly known to be applied to model deep learning architectures, Tensorflow's flexible interface makes it a good candidate for production level data-science pipelines as well.

In this talk, you will learn about the fundamentals of distributing Tensorflow models over multiple computers.

Fabrizio Milo is a deep learning architect and early TensorFlow contributor @

Small a5sz6tzp 400x400 Sam Abrahams on

Machine learning, especially deep learning, is becoming more and more important to integrate into day-to-day business infrastructure across all industries. TensorFlow, open-sourced by Google in 2015, has become one of the more popular modern deep learning frameworks available today, promising to bridge the gap between the development of new models and their deployment.

This talk is an in-depth workshop on the fundamentals of the TensorFlow framework. It aims to prepare listeners to have a firm grasp of the core TensorFlow classes and workflow enabling better comprehension of deep learning models and tutorials built in TensorFlow.

Sam Abrahams is a freelance data scientist and engineer. He is a long-time contributor to the TensorFlow repository and a co-author on the upcoming book TensorFlow for Machine Intelligence.

Small adamg Adam Gibson on

Deep learning is all the rage in advanced analytics. How does it work and how can it scale? Adam Gibson, Data Scientist and Co-founder of Skymind, explains why representational learning is an advance over traditional machine learning techniques. He also gives a demo of a working deep-belief net with a tour through DL4J's API, showing how a DBN extracts features and classifies data.


This talk was given at the SF Data Mining meetup at Trulia.

Small adamg Adam Gibson on

Adam Gibson (Data Scientist and Co-Founder, presents his open-source, distributed deep-learning framework, Deeplearning4j. He demos sentiment analysis and facial recognition tools.


DL4J is a commercial-grade platform written in Java and compatible with Hadoop. Its neural nets work for image recognition, text analysis and speech-to-text. DL4J has implementations of such algorithms as binary and continuous restricted Boltzmann machines, deep-belief nets, denoising autoencoders, convolutional nets and recursive neural tensor networks. Users with a working knowledge of Java will be able to undertake anomaly/fraud detection, recommendation engines and social-media ranking systems, among many other machine learning applications.

This talk was presented at theĀ SF Neural Network Aficionados Discussion Group hosted by NextSpace in San Francisco.


Join Us