By Sophie Curtis on August 05, 2015
Here's the latest news and events from the RE.WORK team!
Deep Learning Summit London: Schedule Announced
What is deep learning and why should we care about it? How are advancements in neural networks going to impact healthcare, manufacturing, and transport in the future? How will this new way of getting intelligence from big data be applied and what problems can it solve?
At the Deep Learning Summit
in London on 24-25 September we'll be discussing a technical overview of the latest advancements in voice recognition, natural language processing, speech recognition, and image processing, as well as the latest applications for deep learning technology and algorithms.
Alison Lowndes, Deep Learning Solutions Architect, NVIDIA
Koray Kavukcuoglu, Research Scientist, Google DeepMind
Blaise Thomson, CEO, VocalIQ
Miriam Redi, Research Scientist, Yahoo Labs
Cees Snoek, Director, QUVA
View the agenda here
Calling Startups Working in Cutting-Edge Technology!
Calling all startups working in breakthrough tech! The third annual RE.WORK Future Technology Summit
, taking place in London on 24-25 September, will
feature a startup exhibition of the most disruptive and innovative startups shaping our future through applying emerging technologies to solve real world challenges.
Topics explored at the summit include:
This is your chance
international exposure of your product/innovation through media outlets
or demo your startup to 400+ global attendees
future collaborators and investors
Find out more here
A Neural Abstraction Pyramid to Semantic RGB-D Perception
Dr. Sven Behnke is Professor and Head of Computer Science at the University of Bonn
, where he also heads the Autonomous Intelligent Systems group. At the Deep Learning Summit
in London, Sven will discuss the Neural Abstraction Pyramid, a deep learning architecture, in which layer-by-layer unsupervised learning creates increasingly abstract image representations. The presentation will also focus on more recent work on deep learning for object-class segmentation of images and semantic RGB-D perception.
We caught up with Sven ahead of the summit on 24-25 September to hear more about his work and the recent advancements in deep learning.
Q: What are your recent developments on the Neural Abstraction Pyramid?
Our recent developments include discriminative training through max-pooling units, object-class segmentation for color and RGB-D images, training with a structured loss for object detection, and the application of recurrent deep networks to surface categorization in RGB-D video.
Q: What are the key factors that have enabled recent advancements in deep learning?
I see three key factors for the recent advances in deep learning. First of all, algorithmic advances, such as discriminative training through max-pooling units, drop-out regularization, and deep architectures which better match the statistics of the data and improve performance on existing problems. Secondly, the collection and annotation of large data sets, such as ImageNet, created new challenges, where deep learning of non-linear, convolutional feature extraction outperformed other methods. Finally, the availability of general-purpose GPUs and other affordable parallel computers made it possible to train deep architectures on large data sets and to optimize their hyper-parameters.
Read the full interview here
Other News not to be Missed:
Until next time!