Results
- Showing results for:
- Reset all filters
Search results
-
Conference paperLane DM, Maurelli F, Kormushev P, et al., 2015,
PANDORA - Persistent Autonomy through Learning, Adaptation, Observation and Replanning
-
Conference paperAthakravi D, Alrajeh D, Broda K, et al., 2015,
Inductive Learning Using Constraint-Driven Bias
, 24th International Conference on Inductive Logic Programming (ILP), Publisher: SPRINGER-VERLAG BERLIN, Pages: 16-32, ISSN: 0302-9743- Author Web Link
- Cite
- Citations: 5
-
Journal articleTakano W, Asfour T, Kormushev P, 2015,
Special Issue on Humanoid Robotics
, Advanced Robotics, Vol: 29 -
Journal articleBimbo J, Kormushev P, Althoefer K, et al., 2015,
Global Estimation of an Object’s Pose Using Tactile Sensing
, Advanced Robotics, Vol: 29 -
Conference paperAhmadzadeh SR, Kormushev P, Caldwell DG, 2014,
Multi-Objective Reinforcement Learning for AUV Thruster Failure Recovery
-
Journal articleKadir SN, Goodman DFM, Harris KD, 2014,
High-dimensional cluster analysis with the masked EM algorithm
, Neural Computation, Vol: 26, Pages: 2379-2394, ISSN: 0899-7667Cluster analysis faces two problems in high dimensions: the "curse of dimensionality" that can lead to overfitting and poor generalization performance and the sheer time taken for conventional algorithms to process large amounts of high-dimensional data. We describe a solution to these problems, designed for the application of spike sorting for nextgeneration, high-channel-count neural probes. In this problem, only a small subset of features provides information about the cluster membership of any one data vector, but this informative feature subset is not the same for all data points, rendering classical feature selection ineffective.We introduce a "masked EM" algorithm that allows accurate and time-efficient clustering of up to millions of points in thousands of dimensions. We demonstrate its applicability to synthetic data and to real-world high-channel-count spike sorting data.
-
Conference paperDallali H, Kormushev P, Tsagarakis N, et al., 2014,
Can Active Impedance Protect Robots from Landing Impact?
-
Conference paperAhmadzadeh SR, Jamisola RS, Kormushev P, et al., 2014,
Learning Reactive Robot Behavior for Autonomous Valve Turning
-
Conference paperJamisola RS, Kormushev P, Bicchi A, et al., 2014,
Haptic Exploration of Unknown Surfaces with Discontinuities
-
Conference paperJamali N, Kormushev P, Caldwell DG, 2014,
Robot-Object Contact Perception using Symbolic Temporal Pattern Learning
-
Conference paperAhmadzadeh SR, Carrera A, Leonetti M, et al., 2014,
Online Discovery of AUV Control Policies to Overcome Thruster Failures
-
Conference paperCarrera A, Karras G, Bechlioulis C, et al., 2014,
Improving a Learning by Demonstration framework for Intervention AUVs by means of an UVMS controller
-
Conference paperJamali N, Kormushev P, Ahmadzadeh SR, et al., 2014,
Covariance Analysis as a Measure of Policy Robustness in Reinforcement Learning
-
Conference paperCarrera A, Palomeras N, Ribas D, et al., 2014,
An Intervention-AUV learns how to perform an underwater valve turning
-
Journal articleDeisenroth MP, Fox D, Rasmussen CE, 2014,
Gaussian Processes for Data-Efficient Learning in Robotics and Control
, IEEE Transactions on Pattern Analysis and Machine Intelligence, ISSN: 0162-8828Autonomous learning has been a promising direction in control and robotics for more than a decade since data-drivenlearning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous reinforcementlearning (RL) approaches typically require many interactions with the system to learn controllers, which is a practical limitation in realsystems, such as robots, where many interactions can be impractical and time consuming. To address this problem, current learningapproaches typically require task-specific knowledge in form of expert demonstrations, realistic simulators, pre-shaped policies, orspecific knowledge about the underlying dynamics. In this article, we follow a different approach and speed up learning by extractingmore information from data. In particular, we learn a probabilistic, non-parametric Gaussian process transition model of the system.By explicitly incorporating model uncertainty into long-term planning and controller learning our approach reduces the effects of modelerrors, a key problem in model-based learning. Compared to state-of-the art RL our model-based policy search method achieves anunprecedented speed of learning. We demonstrate its applicability to autonomous learning in real robot and control tasks.
-
Conference paperLaw M, Russo A, Broda K, 2014,
Inductive Learning of Answer Set Programs
, 14th European Conference on Logics in Artificial Intelligence (JELIA), Publisher: Springer, Pages: 311-325, ISSN: 0302-9743 -
Book chapterMaimari N, Broda K, Kakas A, et al., 2014,
Symbolic Representation and Inference of Regulatory Network Structures
, Logical Modeling of Biological Systems, Publisher: John Wiley & Sons, Inc., Pages: 1-48, ISBN: 9781119005223 -
Conference paperCarrera A, Palomeras N, Hurtos N, et al., 2014,
Learning by demonstration applied to underwater intervention
-
Conference paperTurliuc C-R, Maimari N, Russo A, et al., 2013,
On Minimality and Integrity Constraints in Probabilistic Abduction
, LPAR Logic for Programming,Artificial Intelligence and Reasoning, Publisher: Springer Verlag -
Journal articleGoodman DF, Benichoux V, Brette R, 2013,
Decoding neural responses to temporal cues for sound localization
, eLife, Vol: 2, ISSN: 2050-084XThe activity of sensory neural populations carries information about the environment. This may be extracted from neural activity using different strategies. In the auditory brainstem, a recent theory proposes that sound location in the horizontal plane is decoded from the relative summed activity of two populations in each hemisphere, whereas earlier theories hypothesized that the location was decoded from the identity of the most active cells. We tested the performance of various decoders of neural responses in increasingly complex acoustical situations, including spectrum variations, noise, and sound diffraction. We demonstrate that there is insufficient information in the pooled activity of each hemisphere to estimate sound direction in a reliable way consistent with behavior, whereas robust estimates can be obtained from neural activity by taking into account the heterogeneous tuning of cells. These estimates can still be obtained when only contralateral neural responses are used, consistently with unilateral lesion studies. DOI: http://dx.doi.org/10.7554/eLife.01312.001.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.
Contact us
Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ
To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:
To reach the network manager, Diana O'Malley - including to join the network - please contact: