Mid-January update Kalman Filter implementation & - - PowerPoint PPT Presentation
01/15/16 Mid-January update Kalman Filter implementation & reconstruction debugging Rebecca Carney Student Instrumentation Weekly 1 Kalman Filter in spiking NN - update RMD Carney 01/15/16 TrueNorth neuromorphic chip TrueNorth
01/15/16
RMD Carney 01/15/16
64 x 64 neurosynaptic cores in 28nm 1 kHz effective clock (called a tick, or synchronization point) Tiled, distributed computing and memory Fully connected Best for neural-network-like applications
RMD Carney 01/15/16
NB these aren’t gates, it’s neuroscience symbols for an axon
RMD Carney 01/15/16
Learned connection probabilities (weights) Assigned strengths Binary connections in chip based on probability from training
Synapse ‘strength’ (1 or -1) is assigned before training. Usually random or with other initialization patterns (not important for today). During network training a ‘backward’ traversal through the network updates the probability of a connection being useful. In the final step, a stochastic sampling decides which weights are useful and only those connections are carried through in the model file.
RMD Carney 01/15/16
http://ieeexplore.ieee.org/stamp/stamp.jsp? arnumber=737502
Kalman Filtering and Neural Networks by Simon Haykin
Kalman filters appear to eliminate the need for explicit offline training. Rather, the process of passing data through the data updates the various parameters of the process and measurement equations. However, one of these update steps appears to change the weights
There is no way to update the ‘weights’ of a neuron online in
So my question is: how were you planning to get around this? Is there a different KF implementation that does not require this?
RMD Carney 01/15/16
Spiking Neural Network Decoder for Brain-Machine Interfaces by Julie Dethier, et. al. http://ieeexplore.ieee.org/xpls/abs_all.jsp? arnumber=5910570&tag=1
RMD Carney 01/15/16
Generation HepMC Simulation G4 Hits Digitization G4 Digits Reconstruction Create AOD ESD AOD Analysis Real Data Atlfast
A cluster Individual pixel hits
/afs/cern.ch/work/r/rcarney/private/rc_analysis/run/mySample_edited.InDetDxAOD.pool.root ===========================Event #0/5000===================== ToT vector is empty! tot = (*pix_itr)->auxdataConst< std::vector<int> >("rdo_tot"); if(tot.empty()){ std::cout<<"ToT vector is empty!"<<std::endl; exit(1); }