Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing. However, in practice domain shift often exists, where real-world factors such as lighting and sensor type change between train and test, and classifiers do not generalise from source to target domains. It is impractical to train separate models for all possible situations because ...

Real-world robotics problems often occur in domains that differ significantly from the robot’s prior training environment. For many robotic control tasks, real world experience is expensive to obtain, but data is easy to collect in either an instrumented environment or in simulation. We propose a novel domain adaptation approach for robot perception that adapts visual representations learned on...

Adaptation of visually guided reaching movements in novel visuomotor environments (e.g. wearing prism goggles) comprises not only motor adaptation but also substantial sensory adaptation, corresponding to shifts in the perceived spatial location of visual and proprioceptive cues. Previous computational models of the sensory component of visuomotor adaptation have assumed that it is driven purel...

Neural adaptation underlies the ability of neurons to maximize encoded information over a wide dynamic range of input stimuli. Recent spiking neuron models like the adaptive Spike Response Model implement adaptation as additive fixed-size fast spike-triggered threshold dynamics and slow spike-triggered currents. Such adaptation accurately models neural spiking behavior over a limited dynamic in...

This paper presents a speaker adaptation framework that combines the speaker normalization (SN) training. Because of the varieties among training speakers, more data are required in training and adaptation of speaker independent (SI) acoustic model. In this paper, a very simple but effective normalization method is presented, in which the distortions among different speakers are removed by subt...

This paper describes an approach to the integration of case and models called model-based adaptation (MBA). Under this approach, case-based reasoning is used to find an approximate solution, and model-based reasoning is then used to adapt this approximate solution into a more precise solution. This paper distinguishes two distinct forms of MBA--per]ect-model-based adaptation and approximate-mod...

Recently, there has been an increased interest on the neural mechanisms underlying perceptual decision making. However, the effect of neuronal adaptation in this context has not yet been studied. We begin our study by investigating how adaptation can bias perceptual decisions. We considered behavioral data from an experiment on high-level adaptation-related aftereffects in a perceptual decision...

The adaptive responses of crop genotypes and patterns of genotype x location (G x L) interaction are important to crop improvement as they are the basis for selection for specific adaptation and for elucidation of the causes of G x L interaction. Their legitimate assessment, however, requires yield data for the test genotypes for a large number of sites and over multiple years. Such data are se...

Speaker adaptation aims to estimate a speaker specific acoustic model from a speaker independent one to minimize the mismatch between the training and testing conditions arisen from speaker variabilities. A variety of neural network adaptation methods have been proposed since deep learning models have become the main stream. But there still lacks an experimental comparison between different met...