skip to primary navigation skip to content
Loading Events
Find Events

Event Views Navigation

Past Events

Events List Navigation

July 2017

The 2017 Flynn Lecture: Male and Female IQ- A balance sheet – Professor James Flynn, Department of Politics, University of Orago

July 27 @ 3:30 pm - 5:00 pm

Jim Flynn, the originator of the "Flynn Effect", pays his annual visit to The Psychometrics Centre at Cambridge. This time he updates us on his latest thinking on IQ differences between groups. He will present a complete review of the literature purporting to show gender differences between men and women at various stages of the lifespan. Looking at results from both the Raven Progressive Matrices and the Wechsler tests, he concludes that the hypothesis that girl's intellectual development falls behind…

Find out more »
September 2017

“Translational control of axonal mRNAs can accelerate regeneration” – Jeff Twiss, Department of Biological Sciences, University of South Carolina

September 4 @ 12:00 pm - 1:00 pm

If anyone would like to meet with Prof Twiss after the talk please contact Michael Coleman on mc469@cam.ac.uk.

Find out more »

Towards a whole brain model of perceptual learning – Dr Aaron Seitz, University of California, Riverside

September 4 @ 1:00 pm - 2:00 pm

A hallmark of modern perceptual learning is the nature to which learning effects are specific to the trained stimuli. Such specificity to orientation, spatial location and even eye of training (Karni and Sagi, 1991), has been used as psychophysical evidence of neural basis of learning. However, recent research shows that learning effects once thought to be specific depend on subtleties of the training procedure (Hung and Seitz, 2014) and that within even a simple training task that there are multiple…

Find out more »

Deep learning for autonomous driving – Takayoshi Yamashita (Chubu University)

September 8 @ 11:00 am - 12:00 pm

Convolutional Neural Network (CNN) has a great potential and can be applied to various tasks by changing the relationships between inputs and outputs. Autonomous driving is one of the hot topics among them. In this talk, we will introduce our research using CNNs for tasks such as object detection, semantic segmentation and human pose estimation necessary for realizing automatic driving. We will also introduce the reinforcement learning of driving behavior into simulation.

Find out more »

Towards User-Friendly Image Inpainting: Learning-to-Rank based Image Quality Assessment for Image Inpainting – Mariko Isogawa (NTT Media Intelligence Laboratories)

September 8 @ 11:00 am - 12:00 pm

Image inpainting, which removes and restores unwanted regions in images, is widely acknowledged as a task whose results vary largely depending on the parameter settings. In typical use cases, users have to choose parameters and observe the results by trial and error, until the desired results are obtained. Thus a way to automatically select the best result is needed. In this talk, I will introduce our current research for learning based image quality assessment (IQA) methods for inpainting to support…

Find out more »

Accelerating computation of SVM and DNN by binary approximation – Hironobu Fujiyoshi (Chubu University)

September 8 @ 11:00 am - 12:00 pm

Object detection involves classification of a huge number of detection windows obtained by raster scanning of an input image. In this talk, we introduce binary approximation to accelerate the computation of linear SVM for multi-class classification task. Since the proposed method can replace real-valued inner-product with binary inner-product computations, it's about 200 times faster than the conventional SVM classifiers. We also show that the proposed approach can be extended to enable fast computation of existing deep neural network models and…

Find out more »

The Grammar Variational Autoencoder & Counterfactual Fairness – Dr Matt Kusner

September 12 @ 11:00 am - 12:00 pm

In this talk I'll be covering two research directions I'm really excited about. The first is on improving deep generative models for discrete data using grammars, and the second is on using causality to ensure that machine learning predictions aren't discriminatory. In the first half of the talk I will describe how generative modeling of discrete data such as arithmetic expressions and molecular structures still poses significant challenges. Crucially, state-of-the-art methods often produce outputs that are not valid. We make…

Find out more »

Unbiased Estimation of the Eigenvalues of Large Implicit Matrices – Professor Ryan Adams, Princeton

September 14 @ 11:00 am - 12:00 pm

Many important problems are characterized by the eigenvalues of a large matrix. For example, the difficulty of many optimization problems, such as those arising from the fitting of large models in statistics and machine learning, can be investigated via the spectrum of the Hessian of the empirical loss function. Network data can be understood via the eigenstructure of the Laplacian matrix through spectral graph theory. Quantum simulations and other many-body problems are often characterized via the eigenvalues of the solution…

Find out more »

"MicroRNAs – The master regulators of neural networks development" – Professor Giordano Lippi, The University of California, San Francisco

September 18 @ 12:00 pm - 1:00 pm

Abstract not available

Find out more »

"MicroRNAs – The master regulators of neural networks development" – Professor Giordano Lippi, The University of California, San Francisco

September 18 @ 12:00 pm - 1:00 pm

Abstract not available

Find out more »
+ Export Events