In this lecture, DeepMind Research Scientist Marta Garnelo focuses on sequential data and how machine learning methods have been adapted to process this particular type of structure. Marta starts by introducing some fundamentals of sequence modeling including common architectures designed for this task such as RNNs and LSTMs. She then moves on to sequence-to-sequence decoding and its applications before finishing with some examples of recent applications of sequence models.
Download the slides here:
Find out more about how DeepMind increases access to science here:
Speaker Bio:
Marta is a Research Scientist at DeepMind working on deep generative models and meta learning. During her time at DM she has worked on Generative Query Networks as well as Neural Processes and recently her research focus has shifted towards multi-agent systems. In addition she is currently wrapping up her PhD with Prof Murray Shanahan at Imperial College London where she also did an MSc in Machine Learning.
About the lecture series:
The Deep Learning Lecture Series is a collaboration between DeepMind and the UCL Centre for Artificial Intelligence. Over the past decade, Deep Learning has evolved as the leading artificial intelligence paradigm providing us with the ability to learn complex functions from raw data at unprecedented accuracy and scale. Deep Learning has been applied to problems in object recognition, speech recognition, speech synthesis, forecasting, scientific computing, control and many more. The resulting applications are touching all of our lives in areas such as healthcare and medical research, human-computer interaction, communication, transport, conservation, manufacturing and many other fields of human endeavour. In recognition of this huge impact, the 2019 Turing Award, the highest honour in computing, was awarded to pioneers of Deep Learning.
In this lecture series, leading research scientists from leading AI research lab, DeepMind, deliver 12 lectures on an exciting selection of topics in Deep Learning, ranging from the fundamentals of training neural networks via advanced ideas around memory, attention, and generative modelling to the important topic of responsible innovation.
source
