Skip to content

[$][Workshop][15% Off Before NYE] Putting Deep Learning into Production

Photo of Chris Fregly
Hosted By
Chris F.
[$][Workshop][15% Off Before NYE] Putting Deep Learning into Production

Details

RSVP

https://conf.startup.ml/

https://conf.startup.ml/options/reg 15% Off Discount Code BEFORE New Years Eve: FREGLY

Date

Jan 21, 2017, 9:30a - 5p

Location

Capital One
201 3rd St, 5th Floor
San Francisco

Description

Deep learning models are achieving state-of-the-art results in speech, image/video classification and numerous other areas, but deploying them to production often involves a unique set of challenges including prediction latency, significant training cost, device memory requirements, etc.

This conference will focus on some best practices for deploying deep learning models into production. Speakers will discuss topics like:

• Using pre-trained models

• Improve training speed

• Transfer learning across tasks

• Reducing model size to improve prediction latency

• Reducing model size to fit onto mobile devices

• TensorFlow APIs

• Model Zoo

Speakers and Abstracts

Illia Polosukhin, Google

TensorFlow has taken the deep learning world by storm. This workshop will be led by one of TensorFlow’s main contributors, Illia Polosukhin. Illia’s hands-on workshop will cover:

  • Dropout - both for preventing overfitting and as mechanics to get "what model doesn't know" (confidence of prediction).

  • Augmenting data with adversarial examples - to prevent overfitting and speed up training

  • How to limit technical exploits of your models - e.g. how to use different methods to prevent your model going haywire, using different methods (confidence, adversarial examples, discriminator, separate classifiers or just simple whitelists).

Andrew Tulloch, Facebook

Coming Soon!

Alex Miller, Yelp

Yelp users have uploaded millions of photos, and the rate of photos being added is only increasing. In order to deliver the best experience for these users, the photo understanding team has used deep learning to identify the most beautiful photos and display them throughout the site. In this talk we discuss the motivation for using a deep learning approach, explain how it was implemented, and show some illustrative results.

Andres Rodriguez, Intel Nervana

Deep learning is unlocking tremendous economic value across various market sectors. Individual data scientists can draw from several open source frameworks and basic hardware resources during the very initial investigative phases but quickly require significant hardware and software resources to build and deploy production models. Intel Nervana has built a competitive deep learning platform to make it easy for data scientists to start from the iterative, investigatory phase and take models all the way to deployment. Nervana’s platform is designed for speed and scale, and serves as a catalyst for all types of organizations to benefit from the full potential of deep learning. Example of supported applications include but not limited to automotive speech interfaces, image search, language translation, agricultural robotics and genomics, financial document summarization, and finding anomalies in IoT data. In this talk, we will give an overview of Nervana’s DL platform and get some hands-on experience using this platform to train and execute deep learning models.

Michael Mahoney, UC Berkeley

Coming Soon!

Abhradeep Guha Thakurta, UC Santa Cruz

Machine learning has fundamentally transformed the way we interact with many networked devices around us. However, machine learning's effectiveness also raises profound concerns about privacy --- how we control the collection and use of our information. This tension between collection of users’ information to improve sales revenue of organizations (e.g., via targeted advertising), and the corresponding privacy concerns is increasing at an alarming rate. In this talk, I will introduce privacy preserving algorithms for large-scale machine learning. These algorithms will preserve a rigorous privacy guarantee (differential privacy), and will have provable utility guarantees. Furthermore, they will be amenable to highly distributed systems (e.g., learning on data samples from millions of smartphones). We will illustrate this via a case study of classifying emails into junk vs non-junk. To that end, we will use variants of classic algorithms like gradient descent and cutting plane, and also new algorithmic ideas via functional approximation. If time permits, I will provide some code example for these algorithms in Python.

Chris Fregly, PipelineIO

In this completely demo-based talk, Chris Fregly from PipelineIO will demo the latest 100% open source research in high-scale, fault-tolerant model serving using Tensorflow, Spark ML, Jupyter Notebook, Docker, Kubernetes, and NetflixOSS Microservices.

This talk will discuss the trade-offs of mutable vs. immutable model deployments, on-the-fly JVM byte-code generation, global request batching, miroservice circuit breakers, and dynamic cluster scaling - all from within a Jupyter notebook.

Photo of AI Performance Engineering Meetup (San Francisco, Global) group
AI Performance Engineering Meetup (San Francisco, Global)
See more events
Capital One
201 3rd St, 5th Floor · San Francisco, CA