Gaussian Process Based Filtering for Neural Decoding

Slides:



Advertisements
Similar presentations
Data-Assimilation Research Centre
Advertisements

EKF, UKF TexPoint fonts used in EMF.
A Comprehensive Study on Third Order Statistical Features for Image Splicing Detection Xudong Zhao, Shilin Wang, Shenghong Li and Jianhua Li Shanghai Jiao.
Inferring Hand Motion from Multi-Cell Recordings in Motor Cortex using a Kalman Filter Wei Wu*, Michael Black †, Yun Gao*, Elie Bienenstock* §, Mijail.
A Physically-Based Motion Retargeting Filter SEYOON TAK HYEONG-SEOK KO ACM TOG (January 2005) 方奎力.
Introduction to Mobile Robotics Bayes Filter Implementations Gaussian filters.
Probabilistic Robotics: Kalman Filters
Dr Graeme A. Jones tools from the vision tool box Kalman Tracker - noise and filter design.
Probabilistic Robotics
Comparative survey on non linear filtering methods : the quantization and the particle filtering approaches Afef SELLAMI Chang Young Kim.
Stanford CS223B Computer Vision, Winter 2006 Lecture 11 Filters / Motion Tracking Professor Sebastian Thrun CAs: Dan Maynes-Aminzade, Mitul Saha, Greg.
Probabilistic Robotics Bayes Filter Implementations Gaussian filters.
Application of Kalman filter methods to event filtering and reconstruction for Neutrino Telescopy A. G. Tsirigotis In the framework of the KM3NeT Design.
Platzhalter für Bild, Bild auf Titelfolie hinter das Logo einsetzen Oliver Pajonk, Bojana Rosic, Alexander Litvinenko, Hermann G. Matthies ISUME 2011,
G. Hendeby Recursive Triangulation Using Bearings-Only Sensors TARGET ‘06 Austin Court, Birmingham Recursive Triangulation Using Bearings-Only Sensors.
STUDY, MODEL & INTERFACE WITH MOTOR CORTEX Presented by - Waseem Khatri.
Probabilistic Robotics Robot Localization. 2 Localization Given Map of the environment. Sequence of sensor measurements. Wanted Estimate of the robot’s.
Kalman Filter (Thu) Joon Shik Kim Computational Models of Intelligence.
Probabilistic Robotics Bayes Filter Implementations Gaussian filters.
Probabilistic Robotics Bayes Filter Implementations.
Particle Filters.
Yang Hu University of Pittsburgh Department of Computer Science.
Hilbert Space Embeddings of Conditional Distributions -- With Applications to Dynamical Systems Le Song Carnegie Mellon University Joint work with Jonathan.
Speech Communication Lab, State University of New York at Binghamton Dimensionality Reduction Methods for HMM Phonetic Recognition Hongbing Hu, Stephen.
Unscented Kalman Filter 1. 2 Linearization via Unscented Transform EKF UKF.
V0 analytical selection Marian Ivanov, Alexander Kalweit.
Speech Lab, ECE, State University of New York at Binghamton  Classification accuracies of neural network (left) and MXL (right) classifiers with various.
Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology 1 Adaptive FIR Neural Model for Centroid Learning in Self-Organizing.
Anti-Slug Control Experiments Using Nonlinear Observers
Using Kalman Filter to Track Particles Saša Fratina advisor: Samo Korpar
Nonlinear State Estimation
Brain-Machine Interface (BMI) System Identification Siddharth Dangi and Suraj Gowda BMIs decode neural activity into control signals for prosthetic limbs.
Cameron Rowe.  Introduction  Purpose  Implementation  Simple Example Problem  Extended Kalman Filters  Conclusion  Real World Examples.
Javad Azimi, Ali Jalali, Xiaoli Fern Oregon State University University of Texas at Austin In NIPS 2011, Workshop in Bayesian optimization, experimental.
The Unscented Particle Filter 2000/09/29 이 시은. Introduction Filtering –estimate the states(parameters or hidden variable) as a set of observations becomes.
The Unscented Kalman Filter for Nonlinear Estimation Young Ki Baik.
Status Report about the Investigations to the Test method For the Sun Load Impact Status Report about the Investigations to the Test method For the Sun.
Tijl De Bie John Shawe-Taylor ECS, ISIS, University of Southampton
Building Adaptive Basis Function with Continuous Self-Organizing Map
C. Canton1, J.R. Casas1, A.M.Tekalp2, M.Pardàs1
Outlier Processing via L1-Principal Subspaces
Accurate Robot Positioning using Corrective Learning
PSG College of Technology
Hire Toyota Innova in Delhi for Outstation Tour
Recovery from Occlusion in Deep Feature Space for Face Recognition
Unscented Kalman Filter
Unscented Kalman Filter
Image processing and computer vision
Jincong He, Louis Durlofsky, Pallav Sarma (Chevron ETC)
Paulo Gonçalves1 Hugo Carrão2 André Pinheiro2 Mário Caetano2
A Sensor Location Decision Model for Truck Flow Measurement: Kyung (Kate) Hyun, UC Irvine Previous studies Goal Identifiability of ODs and routes (i.e.,
ريكاوري (بازگشت به حالت اوليه)
Evaluation of Data Fusion Methods Using Kalman Filtering and TBM
Data Driven Brain Tumor Segmentation in MRI Using Probabilistic Reasoning over space and Time Jeffery Solomon, John A. Butman, and Arun Sood MICCAI 2004.
A Real-Time Learning Technique to Predict Cloud-To-Ground Lightning
Goodfellow: Chapter 14 Autoencoders
Hellenic Open University
Pyramid coder with nonlinear prediction
Lecture 17 Kalman Filter.
Unscented Kalman Filter
An AWGN Multiaccess Channel*
Kalman Filtering COS 323.
John H.L. Hansen & Taufiq Al Babba Hasan
6.891 Computer Experiments for Particle Filtering
Review 1+3= 4 7+3= = 5 7+4= = = 6 7+6= = = 7+7+7=
Learning Long-Term Temporal Features
Diagnosis Definition:
Application of Proposed New BES Definition:
Kalman Filters Gaussian MNs
Hsiao-Yu Chiang Xiaoya Li Ganyu “Bruce” Xu Pinshuo Ye Zhanyuan Zhang
Presentation transcript:

Gaussian Process Based Filtering for Neural Decoding Karthik Lakshmanan, Humphrey Hu, Arun Venkatraman April 24, 2013 University of Pittsburgh Sony Pictures http://cs.cmu.edu/~arunvenk/academics/neural/

Setup & Motivation    

Proposed Method Model non-linear observation mapping with Gaussian Processes (GPs) Need to use Unscented Kalman Filter (UKF) However, this can be slow to evaluate…  

Dimensionality Reduction  

Trajectory Reconstruction Neural Reconstruction Results & Conclusion Improved decoding & produced a higher fidelity generative (observation) model Trajectory Reconstruction Final Cursor Position Neural Reconstruction % Improvement of GP-UKF over KF (both non-dim-reduced) 33.6% 42.8% 43.4% % Improvement of GP-UKF (w/PCA) over KF (non-dim-reduced) 22.2% 16.8% - % Improvement of GP-UKF (w/FA) over KF (non-dim-reduced) -0.80% -7.20% (trained on 1/5 of training data)