What we're about
Upcoming events (1)
Please note that Photo ID will be required. Please can attendees ensure their meetup profile name includes their full name to ensure entry. Agenda: - 18:30: Doors open, pizza, beer, networking - 19:00: First talk - 19:45: Break & networking - 20:00: Second talk - 20:45: Close *Sponsors* Man AHL: At Man AHL, we mix machine learning, computer science and engineering with terabytes of data to invest billions of dollars every day. Evolution AI: Build a state-of-the-art NLP pipeline in seconds. *Neural Networks and Decision Trees (Ryutaro Tanno) Abstract: Deep neural networks and decision trees operate on largely separate paradigms; typically, the former performs representation learning with pre-specified architectures, while the latter is characterised by learning hierarchies over pre-specified features with data-driven architectures. We unite the two via adaptive neural trees (ANTs), a model that incorporates representation learning into edges, routing functions and leaf nodes of a decision tree, along with a backpropagation-based training algorithm that adaptively grows the architecture from primitive modules (e.g., convolutional layers). We demonstrate that, whilst achieving competitive performance on classification and regression datasets, ANTs benefit from (i) lightweight inference via conditional computation, (ii) increased interpretability via hierarchical separation of features e.g. learning meaningful class associations, such as separating natural vs. man-made objects, and (iii) a mechanism to adapt the architecture to the size and complexity of the training dataset. Bio: Ryutaro Tanno is a 3rd year PhD student at UCL on a Microsoft Research scholarship. After completing MASt in Mathematics, and MPhil from Computational and Biological Learning group in university of Cambridge, he started his Phd in 2015 under the supervision of Daniel C. Alexander at University College London and Antonio Criminisi of Microsoft Research Cambridge. His main interest lies in developing high-performance machine learning algorithms which are more interpretable and safer to use in healthcare applications. He received a best paper award in MICCAI 2017, the largest international conference on machine learning for medical imaging applications. *Architectures for big scale 2D imagery (Zbigniew Wojna) Abstract: Presentation of research conducted during his PhD at UCL and in collaboration with Google. Primary interest lays in the development of neural architectures for 2D imagery problems in big scale. Will present the recently published analysis of different upsampling methods in the decoder part of visual architectures, together with ongoing extension for GANs; discuss attention mechanism for text recognition and review for what kind of application it can be useful (automatically updating Google Maps based on Google Street View imagery); explain the idea behind Inception and what had to be changed in inception-v3 to have it the best single model on ImageNet 2015 and how does it compare to Resnet architecture. Together with inception, will present winning submission to MS COCO 2016 detection challenge and the extensive analysis of different models and backbone architectures inside. Conclude with short review of UCL effort working with 4096x4096 images at The Digital Mammography DREAM Challenge for breast cancer recognition. Bio: Zbigniew Wojna is deep learning researcher and founder of TensorFlight Inc. company providing instant remote commercial property inspection based on satellite and street view type imagery. Is currently in the final stage of his PhD (with more than 2000 citations) at UCL under the supervision of Prof Iasonas Kokkinos and Prof John Shawe-Taylor. Primary interest lies in finding/solving research problems around 2D machine vision applications usually in big scale. Zbigniew in his PhD career spent most of the time working across different groups in DeepMind, Google Research, and Facebook Research.