Transcript Presentation

Exploring Artificial Neural
Networks to Discover Higgs at
LHC
Using Neural Networks for B-tagging
By Rohan Adur
www.hep.ucl.ac.uk/~radur
Exploring Artificial Neural Networks
to Discover Higgs at LHC
Outline:
• What are Neural Networks and how do
they work?
• How can Neural Networks be used in bjet tagging to discover the Higgs boson?
• What results have I obtained using
Neural Networks to find b-jets?
Neural Networks - Introduction
• Neural Networks simulate neurons in
biological systems
• They are made up of neurons
connected by synapses
• They are able to solve non-linear
problems by learning from experience,
rather than being explicitly programmed
for a particular problem
The Simple Perceptron
• The Simple Perceptron
is the simplest form of a
Neural Network
• It consists of one layer
of input units and one
layer of output units,
connected by weighted
synapses
Output layer
Synapses
connected
by weights
Input
layer
The Simple Perceptron contd.
• Requires a training set,
for which the required
output is known
• Synapse weights start at
random values. A
learning algorithm then
changes the weights
until they give the
correct output and the
weights are frozen
• The trained network can
then be used on data it
has never seen before
Output layer
Synapses
connected
by weights
Input
layer
The Multilayer Perceptron
• The main drawback of
the simple perceptron is
that it is only able to
solve linearly-separable
problems
• Introduce a hidden layer
to produce the
Multilayer Perceptron
• The Multilayer
Perceptron is able to
solve non-linear
problems
Output layer
Synapses
Hidden Layer
Synapse
s
Input
layer
Finding Higgs
• The Higgs boson is
expected to decay to bquarks, which will produce
b-jets
• b-jet detection at LHC is
important in detecting Higgs
• 40 million events happening
per second
• b-taggers must reject light
quark jets
b-tagging
• B mesons are able to
travel a short distance
before decaying, so bjets will originate away
from the primary vertex
• Several b-taggers exist
• IP3D tagger uses the
Impact Parameter of the
b-jets
~ 1mm
Primary
Vertex
IP
B
Secondary
Vertex
B-jets
•SecVtx tagger reconstructs
the secondary vertex and
rejects jets which have a
low probability of coming
from this vertex
IP3D Tagger
•Good amount of separation between b-jets and light jets
b-tagger performance
Neural Network for b-tagging
• The current best tagger is a combination
of IP3D and SV1 tag weights
• Using Neural Networks, can this tagger
be combined with others to provide
better separation?
The Multilayer Perceptron and b-tagging
• The TMultiLayerPerceptron class is an
implementation of a Neural Network built into the
ROOT framework
• It contains several learning methods. The best was
found to be the default BFGS method
• Train with output = 1 for signal and output = 0 for
background
• The b-tagging weights were obtained using the
ATHENA 10.0.1 release
• The data was obtained from Rome ttbar AOD files
• Once extracted, the weights were used to train the
Neural Network
Results
• 5 Inputs used: Transverse momentum, IP3D tag, SV1
tag, SecVtx Tag and Mass
• 12 Hidden units and 1 Output unit
Results Contd.
Results Contd.
Rejection rates
Efficiency
IP3D+SV1
Neural Network
60%
88
136
50%
175
387
Mistagging efficiency
Efficiency
IP3D+SV1
Neural Network
60%
1.14%
0.73%
50%
0.57%
0.26%
At fixed rejection
Rejection
IP3D+SV1
Neural Network
100
57%
62%
Discussion of Results
• Using a Neural Network, b-taggers can be
combined to provide up to double the purity at
fixed efficiency
• At fixed rejection rate, the Neural Network
provides 5% more signal than the IP3D+SV1
tagger alone
• Neural Network performance is not always
reproducible. Each time training is
undertaken a different network is produced
Conclusions
• Neural Networks are a powerful tool for bjet classification
• Neural Networks can be used to
significantly increase b-tagging
efficiency/rejection ratios and could be
useful in the search for Higgs
• Training a Neural Network on real data
will be the next hurdle