Double Talk Week
Speaker: Dr Thomas Sauerwald (Computer Lab)
Title: Multiple Random Walks
Abstract: Consider a simple random walk on a finite network. The expected time it takes for a single walk to visit all nodes is a well-studied quantity and has been computed for many topologies including paths, grids, random graphs and hypercubes. But how long does it take for two or more independently running random walks? This talk will explain why this may be an interesting question and present a few surprising results.
Thursday 16 February, 6:15PM
Speaker: Dr Sander Dieleman (Google DeepMind)
Title: Deep learning for music recommendation and generation
Abstract: The advent of deep learning has made it possible to extract high-level information from perceptual signals without having to specify manually and explicitly how to obtain it; instead, this can be learned from examples. This creates opportunities for automated content analysis of musical audio signals. In this talk, I will discuss how deep learning techniques can be used for audio-based music recommendation. I will also briefly discuss my ongoing work on music generation with WaveNet.
Both talks will take place in the Winstanley Lecture Theatre. As usual there will be free refreshments 15 minutes before the talk. The talk on Monday is for members only, but there will be a chance to sign up for TMS life membership for £2.50. The talk on Thursday is free for all.