#LTM - TensorFlow and ML models - applications: medical; self-driving cars

Hey there, we're back with LTM September meetup covering some interesting topics of Tendorflow image segmentation in applications for self-driving cars and medical processes.

Agenda:

6:15 - 6:25 Register and grab a drink

6:30 - 7:00 Using Convolutional LSTMs for video prediction. Applications to self-driving cars and medical image processing (Armando Vieira, Data Scientist @ ContextVision)

7:10 - 7:30 Break time - networking, food & drinks!

7:30 - 7:50 - How the absence of big data doesn’t stop you from learning cool stuff (Dan Busbridge, Machine Learning Scientist @ Babylon Health)

7:50 - 8:10 - Medical validation of non-interpretable models. How can you deploy ML models and be confident that the system remains safe for the end-user? (Nils Hammerla - Machine Learning Scientist @ Babylon Health)

8:20 - wrap up and heading to a local pub (tbc) to continue conversation

--------------------------

1st session: Using Convolutional LSTMs for video prediction. Applications to self-driving cars and medical image processing

Armando Vieira (https://www.linkedin.com/in/asvieira/) (@sairmais (https://twitter.com/sairmais)) - Data Scientist @ ContextVision (http://www.contextvision.com/)

Convolutional LSTM are a class of recurrent network with Long Short Term Memory (LSTM) units applied over convolutional networks (CNN). They are particularly useful to for unsupervised videos analysis, either image segmentation, classification of annotation.
We will present how to create a convolutional LSTM model in Keras and Tensorflow for image segmentation and show some results for self-driving cars and for annotation of arteries and veins on ultra-sound videos.

--------------------------

2nd session: How the absence of big data doesn’t stop you from learning cool stuff

Dan Busbridge (https://www.linkedin.com/in/danbusbridge/) (@danbusbridge (https://twitter.com/danbusbridge)) - Machine Learning Scientist @ Babylon Health

Dan prototypes software applications that use deep reinforcement learning to solve problems in healthcare. Before this, Dan used social network analysis to prevent financial and cyber crime on a global scale, and in a previous life I was a theoretical particle physicist. He specialises in TensorFlow and Spark technologies.

--------------------------

3rd session: Medical validation of non-interpretable models. How can you deploy ML models and be confident that the system remains safe for the end-user?

Nils Hammerla (http://scholar.google.co.uk/citations?user=Qk_ziKsAAAAJ) - Machine Learning Scientist @ Babylon Health

Nils is an applied machine learning researcher with more than 5 years of experience. In his work Nils aims to bridge the gap between the machine learning community and practical application domains like digital healthcare and human computer interaction. His research interest lies in the computational analysis of behaviour, and in how systems can be designed that are sufficiently robust towards naturalistic settings like the private home and real-life interactive applications.

Please see Nils'es google scholar account for an up-to-date list of his publications:
http://scholar.google.co.uk/citations?user=Qk_ziKsAAAAJ

----------------------------

Thank you our sponsors:

Babylon Health (https://www.babylonhealth.com/) (@babylonhealth (https://twitter.com/babylonhealth))

Babylon was founded with a single purpose: To put an accessible and affordable health service in the hands of every person on earth.
How? We’ll do this by combining the ever growing computing power of machines, with hand-picked medical experts to create a comprehensive, immediate and personalised health service and making it universally available.

----------------------------

YLD (https://twitter.com/YLDio)
YLD is one of London’s fastest growing software engineering consultancies working with European brands such as The Economist, Trainline and Thomas Cook.

We augment our clients’ teams with some of the best JavaScript engineers in Europe and help our clients win by employing the best software engineering practices and introducing cutting edge technologies.

Our ethos is defined by a commitment to the open source community - we aim to create a long standing engineering culture and delivery capability in each piece of work we do. We don’t stop until we get there.

Check us out at YLD Blog (https://blog.yld.io/) and Tech Talks YLD (https://www.youtube.com/channel/UCPXA8SlHzOsPNYlXGKZRPdg/featured) channel for more talks expert tech commentary; join the conversation on Twitter @YLDio (https://twitter.com/YLDio) and on LinkedIn!

---------------------------------------------------------------------------------
***Please note that as per security policies, attendees must provide their full names when RSVP. If your meetup.com username does not include your full name, please send a private message to the organiser Greta enclosing your full name. Thanks! ***

Please could you fill in the Babylon form to register your attendance here: https://goo.gl/forms/TyaBdhpkgysBc9aC2

Looking forward to seeing you soon!

#LTM team