
Deadline Driven Design
Featuring Jim Parr
A Formula One team needs to identify the optimal car set up before the start of a race with limited wind tunnel and CPU hours. A UAV designer may be tasked with the rapid development of a sensorcraft for specific flight conditions and payload in response to a environmental accident or volcanic...
machinelearning 
Algorithms that crack quantum mechanics: from atoms to real materials
Featuring Mattia Fiorentini
Since the rise of nanotechnology increasing efforts have been made to develop materialdesign strategies directly from the first principles of matter. In particular, the properties of any materials, even the ones that have not been synthesized yet, can be predicted by solving the equations of...
exploration data algorithm clustering conjugategradient fouriertransform materialdesign quantummechanics bigo 
Classifying planktons with deep neural networks
Featuring Sander Dieleman
Deep neural networks have become very popular for solving computer vision problems in recent years. This talk is an overview of a practical application of this approach: I'll show how our team of 7 built a model for the automated classification of plankton based on convolutional neural...
exploration data deeplearning kaggle convolutionalneuralnetworks neuralnetwork 
A broad view on word vectors.
Featuring Dmitrijs Milajevs
An overview of lexical distributional semantics, a field of computational linguistics that is concerned with word meaning representation as vectors in a highly dimensional vector space. The talk will go trough the historical overview and recent advances in the field and some of its applications.
... 
Practicalities of analysing biosignals
Featuring Emlyn Clay
This will be a talk on the data structures and the analytical techniques to go about analysing electrophysiology signals from the body.

Greedy Algorithms for Testing
Featuring David MacIver
Testing libraries like Quickcheck generate random data to break tests, then greedily apply a simplification function to prune them down to more legible examples.

Reinforcement Learning and its use in realtime applications
Featuring Charles Galambos
Reinforcement Learning is a powerful technique for identifying the best actions to take to achieve a goal.

Clever Hans, Clever Algorithms: Are your machine learnings learning what you think?
Featuring Bob Sturm
In machine learning, generalisation is the aim, and overfitting is the bane; but just because one avoids the latter does not guarantee the former. Of particular importance in some applications of machine learning is the “sanity" of the models learnt. In this talk Bob Sturm discusses one...
machinelearning algorithm datastructures 
Information surprise or how to find interesting data
Featuring Oleksandr Pryymak
Information surprise or how to find interesting data.

Image Recompression
Featuring John GrahamCumming
GIF, PNG, JPEG. All have different ways of compressing images. This talk will explain how those common image types are compressed and how it's possible to recompress images to achieve the smallest file size possible.
compression imagecompression 
Multiinstance deep learning
Deep learning has been making spectacular improvements towards computer understanding of highdimensional, sensory, data. Recently human performance has been surpassed on the 1000 class Imagenet benchmark. These rapid developments have, however, left many gaps in our understanding of the power of...
deeplearning machinelearning 
Squishy Maps
Featuring Robin Houston
Squishy maps – more formally known as continuous area cartograms – are a fun and useful way to represent certain sorts of geographic data. Various algorithms have been used to construct them over the years, but my favourite is the 2004 diffusionbased method invented by Michael Gastner and Mark...
data machinelearning algorithm parallelprogramming 
Learning Quantum Mechanics : Machines versus Humans
Featuring Alan Nichol
All of materials science, chemistry, and biology can in principle be predicted from the equations of quantum mechanics. In practice this turns out to be nontrivial. We will look at how machine learning algorithms, in conjunction with theory devised over the last century, are enabling a...
exploration data machinelearning quantummechanics 
The next generation in highperformance messaging
Featuring Martin Thompson
Does TCP not meet your required latency consistently? Is UDP not reliable enough? Do you need to multicast? What about flow control, congestion control, and a means to avoid head of line blocking that can be integrated with the application? Or perhaps you're just fascinated by how to design...
exploration devops lowlatency lockfree mechanicalsympathy aeron reliability performance quantummechanics 
The Slow Fourier Transform
Featuring Tom Nielsen
The Fourier transform is a cornerstone of modern data analysis.
bayesian fourier data machinelearning 
The Master Theorem
Featuring Christina Nicolau
The master theorem provides an out of the box method for computing the complexity of certain classes of Divide et Impera algorithms. We'll be looking inside the box to see how the magic happens!
algorithm data 
The Burrows Wheeler Transform for DNA sequence analysis
Featuring Ole SchulzTrieglaff
The BurrowsWheeler Transform (BWT) is an algorithm used in wellknown data compression tools such as bzip2. It works by permuting the input characters in the text and grouping similar characters close to each other. This is useful for subsequent compression by runlength encoding or...
algorithm burrowswheelertransform data machinelearning 
Gibbs Sampling: Some Theory and Some Practice
Featuring Dominic Steinitz
This talk introduces the MetropolisHastings Algorithm and Gibbs Sampling describing some of theory and giving some very simple examples from statistics using Haskell, JAGS (via R) and STAN (via R)and a more complex example from physics (the Ising Model).
haskell 
A Gentle Introduction to Mad Computer Science
Featuring Bodil Stokke
Want to find out why everyone who is anyone is talking about Idris? Come join functional programming expert, Bodil Stokke for a gentle introduction.
dependenttypes idris functionalprogramming
 First
 « Previous
 Page 2 of 3
 Next »
 Last