TensorFlow and Deep Learning : NIPS

Since the community seemed to be very interested in what happened at NIPS 2017 (the biggest / most notorious/noteworthy Neural Networks conference, which took place last December in Long Beach, California), we're having a session to present a recap of interesting developments that were presented there.

We have 4 talks for this month's event:

1. Martin Andrews will review some of the 'hot topics' presented in the opening tutorial session "Deep Learning: Practice and Trends. Nando de Freitas, Scott Reed, Oriol Vinyals".
2. Olzhas Akpambetov will be presenting "Intro to Capsule networks with dynamic routing (and expectation maximisation routing)", a look at the papers around the new concept Geoffrey Hinton and team presented called Capsule Networks.
3. Chaitanya Joshi will be presenting the paper "Personalization in Goal-Oriented Dialog" which he co-wrote and was featured in the Conversational Agents Workshop.
4. Sam Witteveen will be looking at the developments in the space of ML that creates other ML models, which were featured in the AutoML and Learning to Learn papers. These techniques have produced NASnet which is one of the best models for ImageNet to-date.

---

Talks will start at 7pm (Google's A/V equipment permitting) and end at around 9pm, at which point people normally come up to the front for a bit of a chat with each other, and the speakers.