SlideShare a Scribd company logo
1 of 1
Download to read offline
Autocorrect and Neural Networks
Adam Blevins
Dr. Kasper Peeters
Basic Idea: A Neural Network is similar to Artificial Intelligence - it can teach itself like autocorrect.
Input = miktex
Network
Calculations
Output = Molten
Target = MikTeX
Network
Learning Occurs
Trained Output
= MikTeX
You type ”miktex” into your phone and it autocorrects to ”molten”. You then delete molten and once again type MikTeX as
required and the phone learns the word MikTeX as the correction for miktex for the future.
What is a Neural Network?
An Artificial Neural Network (ANN) is effectively a computer
program that learns to interpret large amounts of data. We
present the network with a training set, a learning algorithm
makes corrections to the calculations within and this repeats
until the network is suitably trained. One of the simplest
examples of an ANN takes the following form:
x
b
σ
σ
b
Inputs Hidden Units Output Unit
w
f(x)
Figure 1: A small ANN architecture example
The circles are called nodes and the text within them defines
their outputs. x is the input with f(x) the respective network
output, b is a constant and σ is a sigmoid function for example,
tanh(y) where the input to the node is y. w represents the
weight of a connection between nodes where each arrow
represents a weighted connection. A network may have more
units in each layer and may have many more layers to allow for
more complex calculations.
Uses of Neural Networks
In addition to their use with autocorrect and ability to discover
patterns in large data sets, Neural Networks are also commonly
used for:
1. Image recognition, particularly facial recognition, for
example identifying a criminal using a database of
mugshots.
2. Character recognition which is very popular nowadays,
especially within technology like the Galaxy Note in which
writing with a stylus is commonplace.
3. Function interpolation
The Network Calculations
Each node has a set of connections to nodes from the previous
layer. Defining the output of a node as yi, then the input to a
node j is the sum of the outputs multiplied by their respective
weighted connection:
inputj =
i
yiwji (1)
An example output yi of node i for the sigmoid nodes in Figure
1 is tanh(inputi). Now the next important thing is the
learning algorithm. The most common algorithm is called the
Backpropagation algorithm [1]. The weights are changed with
regards to the following equation:
∆wji = η
∂E
∂wji
(2)
where η is a constant which controls the magnitude of change
and E is the error as a function of the weights. The error
function E has many local minima and for an accurate system
we want to converge on the global minimum for smallest error.
The Error Function
The error depends upon the weights of the network. If we
consider a very simple network in which the error only depends
on one weight, we can imagine it looks something like this:
Figure 2: An error function dependent on one weight
To maximise the accuracy of the trained network, the
Backpropagation algorithm needs to converge on the global
minimum. This depends on a number of factors, not least the
learning rate η from Equation (2). If our first error is stuck in
the local minima, then for η too small, the weight change could
be too small to escape the local minima. If η is too big we
could jump over the global minimum entirely and cause
divergence. We want a method of initialising weights that gives
us the greatest chance of reaching the global minimum.
Pre-training a Neural Network
Pre-training is a method of finding initial weights for the
Neural Network before normal training. The common
technique uses autoencoders. Autoencoders take 2 consecutive
layers, beginning with the input and first hidden layer, and use
the Backpropagation algorithm to train this subnetwork. The
autoencoder mirrors the leftmost layer (represented by the
magenta) to function as shown:
Figure 3: An example autoencoder with two input nodes and
one hidden node
The original training data X is used, and the fewer nodes in
the hidden layer allow for dimension reduction, providing a
simplified output of X, say set Y . Y holds the key
characteristics of set X. The next two layers are trained
similarly using set Y and so on until the entire network is
pre-trained. The network is then rebuilt with the pre-trained
weights. This allows a starting set of weights closer to the
global minimum which gives a greater chance of convergence, as
well as a greater rate of convergence.
Recommended Further Reading
The work of Geoffrey Hinton, a leading researcher in Neural
Nets (whom gave significant contribution to the understanding
of the Backpropagation algorithm alongside David Rumelhart
and Ronald Williams in 1985 [2]) would be encouraged.
References
[1] Michael Nielsen, 2014,
http://neuralnetworksanddeeplearning.com/chap2.html
[2] Rumelhart et. al, 1985, Learning internal representations
by error propagation.

More Related Content

What's hot

Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learningAntonio Rueda-Toicen
 
Community detection
Community detectionCommunity detection
Community detectionScott Pauls
 
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...Seonho Park
 
Equations différentielles, DUT MP, CM 2
Equations différentielles, DUT MP, CM 2Equations différentielles, DUT MP, CM 2
Equations différentielles, DUT MP, CM 2Christophe Palermo
 
Yoav Goldberg: Word Embeddings What, How and Whither
Yoav Goldberg: Word Embeddings What, How and WhitherYoav Goldberg: Word Embeddings What, How and Whither
Yoav Goldberg: Word Embeddings What, How and WhitherMLReview
 
BRAIN TUMOR MRI IMAGE SEGMENTATION AND DETECTION IN IMAGE PROCESSING
BRAIN TUMOR MRI IMAGE SEGMENTATION AND DETECTION IN IMAGE PROCESSINGBRAIN TUMOR MRI IMAGE SEGMENTATION AND DETECTION IN IMAGE PROCESSING
BRAIN TUMOR MRI IMAGE SEGMENTATION AND DETECTION IN IMAGE PROCESSINGDharshika Shreeganesh
 
Graph neural networks overview
Graph neural networks overviewGraph neural networks overview
Graph neural networks overviewRodion Kiryukhin
 
Artificial Neural Networks Lect3: Neural Network Learning rules
Artificial Neural Networks Lect3: Neural Network Learning rulesArtificial Neural Networks Lect3: Neural Network Learning rules
Artificial Neural Networks Lect3: Neural Network Learning rulesMohammed Bennamoun
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and ApplicationsEmanuele Ghelfi
 
Introduction to Generative Adversarial Networks
Introduction to Generative Adversarial NetworksIntroduction to Generative Adversarial Networks
Introduction to Generative Adversarial NetworksBennoG1
 
Acquired macular diseases
Acquired macular diseasesAcquired macular diseases
Acquired macular diseasesSamhaa Mohammed
 
NEURAL NETWORKS
NEURAL NETWORKSNEURAL NETWORKS
NEURAL NETWORKSESCOM
 
Seminar Neuro-computing
Seminar Neuro-computingSeminar Neuro-computing
Seminar Neuro-computingAniket Jadhao
 

What's hot (20)

Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learning
 
Community detection
Community detectionCommunity detection
Community detection
 
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
 
Equations différentielles, DUT MP, CM 2
Equations différentielles, DUT MP, CM 2Equations différentielles, DUT MP, CM 2
Equations différentielles, DUT MP, CM 2
 
Yoav Goldberg: Word Embeddings What, How and Whither
Yoav Goldberg: Word Embeddings What, How and WhitherYoav Goldberg: Word Embeddings What, How and Whither
Yoav Goldberg: Word Embeddings What, How and Whither
 
Graph Based Pattern Recognition
Graph Based Pattern RecognitionGraph Based Pattern Recognition
Graph Based Pattern Recognition
 
BRAIN TUMOR MRI IMAGE SEGMENTATION AND DETECTION IN IMAGE PROCESSING
BRAIN TUMOR MRI IMAGE SEGMENTATION AND DETECTION IN IMAGE PROCESSINGBRAIN TUMOR MRI IMAGE SEGMENTATION AND DETECTION IN IMAGE PROCESSING
BRAIN TUMOR MRI IMAGE SEGMENTATION AND DETECTION IN IMAGE PROCESSING
 
Graph neural networks overview
Graph neural networks overviewGraph neural networks overview
Graph neural networks overview
 
Densenet CNN
Densenet CNNDensenet CNN
Densenet CNN
 
Artificial Neural Networks Lect3: Neural Network Learning rules
Artificial Neural Networks Lect3: Neural Network Learning rulesArtificial Neural Networks Lect3: Neural Network Learning rules
Artificial Neural Networks Lect3: Neural Network Learning rules
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and Applications
 
Introduction to Generative Adversarial Networks
Introduction to Generative Adversarial NetworksIntroduction to Generative Adversarial Networks
Introduction to Generative Adversarial Networks
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
 
Acquired macular diseases
Acquired macular diseasesAcquired macular diseases
Acquired macular diseases
 
NEURAL NETWORKS
NEURAL NETWORKSNEURAL NETWORKS
NEURAL NETWORKS
 
Report (1)
Report (1)Report (1)
Report (1)
 
ShortStoryPPT.pptx
ShortStoryPPT.pptxShortStoryPPT.pptx
ShortStoryPPT.pptx
 
Neural network
Neural networkNeural network
Neural network
 
Seminar Neuro-computing
Seminar Neuro-computingSeminar Neuro-computing
Seminar Neuro-computing
 
Support vector machines
Support vector machinesSupport vector machines
Support vector machines
 

Similar to Neural Networks on Steroids (Poster)

Web Spam Classification Using Supervised Artificial Neural Network Algorithms
Web Spam Classification Using Supervised Artificial Neural Network AlgorithmsWeb Spam Classification Using Supervised Artificial Neural Network Algorithms
Web Spam Classification Using Supervised Artificial Neural Network Algorithmsaciijournal
 
Web spam classification using supervised artificial neural network algorithms
Web spam classification using supervised artificial neural network algorithmsWeb spam classification using supervised artificial neural network algorithms
Web spam classification using supervised artificial neural network algorithmsaciijournal
 
Modeling of neural image compression using gradient decent technology
Modeling of neural image compression using gradient decent technologyModeling of neural image compression using gradient decent technology
Modeling of neural image compression using gradient decent technologytheijes
 
Handwritten Digit Recognition using Convolutional Neural Networks
Handwritten Digit Recognition using Convolutional Neural  NetworksHandwritten Digit Recognition using Convolutional Neural  Networks
Handwritten Digit Recognition using Convolutional Neural NetworksIRJET Journal
 
2.5 backpropagation
2.5 backpropagation2.5 backpropagation
2.5 backpropagationKrish_ver2
 
Cryptography using artificial neural network
Cryptography using artificial neural networkCryptography using artificial neural network
Cryptography using artificial neural networkMahira Banu
 
Image Recognition With the Help of Auto-Associative Neural Network
Image Recognition With the Help of Auto-Associative Neural NetworkImage Recognition With the Help of Auto-Associative Neural Network
Image Recognition With the Help of Auto-Associative Neural NetworkCSCJournals
 
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in RUnderstanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in RManish Saraswat
 
Electricity Demand Forecasting Using Fuzzy-Neural Network
Electricity Demand Forecasting Using Fuzzy-Neural NetworkElectricity Demand Forecasting Using Fuzzy-Neural Network
Electricity Demand Forecasting Using Fuzzy-Neural NetworkNaren Chandra Kattla
 

Similar to Neural Networks on Steroids (Poster) (20)

Web Spam Classification Using Supervised Artificial Neural Network Algorithms
Web Spam Classification Using Supervised Artificial Neural Network AlgorithmsWeb Spam Classification Using Supervised Artificial Neural Network Algorithms
Web Spam Classification Using Supervised Artificial Neural Network Algorithms
 
Web spam classification using supervised artificial neural network algorithms
Web spam classification using supervised artificial neural network algorithmsWeb spam classification using supervised artificial neural network algorithms
Web spam classification using supervised artificial neural network algorithms
 
N ns 1
N ns 1N ns 1
N ns 1
 
MNN
MNNMNN
MNN
 
Unit ii supervised ii
Unit ii supervised iiUnit ii supervised ii
Unit ii supervised ii
 
Modeling of neural image compression using gradient decent technology
Modeling of neural image compression using gradient decent technologyModeling of neural image compression using gradient decent technology
Modeling of neural image compression using gradient decent technology
 
Neural network
Neural networkNeural network
Neural network
 
Handwritten Digit Recognition using Convolutional Neural Networks
Handwritten Digit Recognition using Convolutional Neural  NetworksHandwritten Digit Recognition using Convolutional Neural  Networks
Handwritten Digit Recognition using Convolutional Neural Networks
 
ai7.ppt
ai7.pptai7.ppt
ai7.ppt
 
2.5 backpropagation
2.5 backpropagation2.5 backpropagation
2.5 backpropagation
 
Multi Layer Network
Multi Layer NetworkMulti Layer Network
Multi Layer Network
 
Cryptography using artificial neural network
Cryptography using artificial neural networkCryptography using artificial neural network
Cryptography using artificial neural network
 
Cnn
CnnCnn
Cnn
 
Image Recognition With the Help of Auto-Associative Neural Network
Image Recognition With the Help of Auto-Associative Neural NetworkImage Recognition With the Help of Auto-Associative Neural Network
Image Recognition With the Help of Auto-Associative Neural Network
 
ai7.ppt
ai7.pptai7.ppt
ai7.ppt
 
Deep Learning Survey
Deep Learning SurveyDeep Learning Survey
Deep Learning Survey
 
A Study On Deep Learning
A Study On Deep LearningA Study On Deep Learning
A Study On Deep Learning
 
Deep learning (2)
Deep learning (2)Deep learning (2)
Deep learning (2)
 
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in RUnderstanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R
 
Electricity Demand Forecasting Using Fuzzy-Neural Network
Electricity Demand Forecasting Using Fuzzy-Neural NetworkElectricity Demand Forecasting Using Fuzzy-Neural Network
Electricity Demand Forecasting Using Fuzzy-Neural Network
 

Recently uploaded

Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )aarthirajkumar25
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfSwapnil Therkar
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...Sérgio Sacani
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxAleenaTreesaSaji
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...RohitNehra6
 
A relative description on Sonoporation.pdf
A relative description on Sonoporation.pdfA relative description on Sonoporation.pdf
A relative description on Sonoporation.pdfnehabiju2046
 
Boyles law module in the grade 10 science
Boyles law module in the grade 10 scienceBoyles law module in the grade 10 science
Boyles law module in the grade 10 sciencefloriejanemacaya1
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsSérgio Sacani
 
Cultivation of KODO MILLET . made by Ghanshyam pptx
Cultivation of KODO MILLET . made by Ghanshyam pptxCultivation of KODO MILLET . made by Ghanshyam pptx
Cultivation of KODO MILLET . made by Ghanshyam pptxpradhanghanshyam7136
 
Types of different blotting techniques.pptx
Types of different blotting techniques.pptxTypes of different blotting techniques.pptx
Types of different blotting techniques.pptxkhadijarafiq2012
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfSumit Kumar yadav
 
Orientation, design and principles of polyhouse
Orientation, design and principles of polyhouseOrientation, design and principles of polyhouse
Orientation, design and principles of polyhousejana861314
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsAArockiyaNisha
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real timeSatoshi NAKAHIRA
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡anilsa9823
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxgindu3009
 
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxPhysiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxAArockiyaNisha
 
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...jana861314
 

Recently uploaded (20)

Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptx
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...
 
A relative description on Sonoporation.pdf
A relative description on Sonoporation.pdfA relative description on Sonoporation.pdf
A relative description on Sonoporation.pdf
 
Boyles law module in the grade 10 science
Boyles law module in the grade 10 scienceBoyles law module in the grade 10 science
Boyles law module in the grade 10 science
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
 
Cultivation of KODO MILLET . made by Ghanshyam pptx
Cultivation of KODO MILLET . made by Ghanshyam pptxCultivation of KODO MILLET . made by Ghanshyam pptx
Cultivation of KODO MILLET . made by Ghanshyam pptx
 
Types of different blotting techniques.pptx
Types of different blotting techniques.pptxTypes of different blotting techniques.pptx
Types of different blotting techniques.pptx
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdf
 
Orientation, design and principles of polyhouse
Orientation, design and principles of polyhouseOrientation, design and principles of polyhouse
Orientation, design and principles of polyhouse
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based Nanomaterials
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real time
 
The Philosophy of Science
The Philosophy of ScienceThe Philosophy of Science
The Philosophy of Science
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
 
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxPhysiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
 
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
 

Neural Networks on Steroids (Poster)

  • 1. Autocorrect and Neural Networks Adam Blevins Dr. Kasper Peeters Basic Idea: A Neural Network is similar to Artificial Intelligence - it can teach itself like autocorrect. Input = miktex Network Calculations Output = Molten Target = MikTeX Network Learning Occurs Trained Output = MikTeX You type ”miktex” into your phone and it autocorrects to ”molten”. You then delete molten and once again type MikTeX as required and the phone learns the word MikTeX as the correction for miktex for the future. What is a Neural Network? An Artificial Neural Network (ANN) is effectively a computer program that learns to interpret large amounts of data. We present the network with a training set, a learning algorithm makes corrections to the calculations within and this repeats until the network is suitably trained. One of the simplest examples of an ANN takes the following form: x b σ σ b Inputs Hidden Units Output Unit w f(x) Figure 1: A small ANN architecture example The circles are called nodes and the text within them defines their outputs. x is the input with f(x) the respective network output, b is a constant and σ is a sigmoid function for example, tanh(y) where the input to the node is y. w represents the weight of a connection between nodes where each arrow represents a weighted connection. A network may have more units in each layer and may have many more layers to allow for more complex calculations. Uses of Neural Networks In addition to their use with autocorrect and ability to discover patterns in large data sets, Neural Networks are also commonly used for: 1. Image recognition, particularly facial recognition, for example identifying a criminal using a database of mugshots. 2. Character recognition which is very popular nowadays, especially within technology like the Galaxy Note in which writing with a stylus is commonplace. 3. Function interpolation The Network Calculations Each node has a set of connections to nodes from the previous layer. Defining the output of a node as yi, then the input to a node j is the sum of the outputs multiplied by their respective weighted connection: inputj = i yiwji (1) An example output yi of node i for the sigmoid nodes in Figure 1 is tanh(inputi). Now the next important thing is the learning algorithm. The most common algorithm is called the Backpropagation algorithm [1]. The weights are changed with regards to the following equation: ∆wji = η ∂E ∂wji (2) where η is a constant which controls the magnitude of change and E is the error as a function of the weights. The error function E has many local minima and for an accurate system we want to converge on the global minimum for smallest error. The Error Function The error depends upon the weights of the network. If we consider a very simple network in which the error only depends on one weight, we can imagine it looks something like this: Figure 2: An error function dependent on one weight To maximise the accuracy of the trained network, the Backpropagation algorithm needs to converge on the global minimum. This depends on a number of factors, not least the learning rate η from Equation (2). If our first error is stuck in the local minima, then for η too small, the weight change could be too small to escape the local minima. If η is too big we could jump over the global minimum entirely and cause divergence. We want a method of initialising weights that gives us the greatest chance of reaching the global minimum. Pre-training a Neural Network Pre-training is a method of finding initial weights for the Neural Network before normal training. The common technique uses autoencoders. Autoencoders take 2 consecutive layers, beginning with the input and first hidden layer, and use the Backpropagation algorithm to train this subnetwork. The autoencoder mirrors the leftmost layer (represented by the magenta) to function as shown: Figure 3: An example autoencoder with two input nodes and one hidden node The original training data X is used, and the fewer nodes in the hidden layer allow for dimension reduction, providing a simplified output of X, say set Y . Y holds the key characteristics of set X. The next two layers are trained similarly using set Y and so on until the entire network is pre-trained. The network is then rebuilt with the pre-trained weights. This allows a starting set of weights closer to the global minimum which gives a greater chance of convergence, as well as a greater rate of convergence. Recommended Further Reading The work of Geoffrey Hinton, a leading researcher in Neural Nets (whom gave significant contribution to the understanding of the Backpropagation algorithm alongside David Rumelhart and Ronald Williams in 1985 [2]) would be encouraged. References [1] Michael Nielsen, 2014, http://neuralnetworksanddeeplearning.com/chap2.html [2] Rumelhart et. al, 1985, Learning internal representations by error propagation.