Download presentation
Presentation is loading. Please wait.
1
Hub Queue Size Analyzer Implementing Neural Networks in practice
2
Task Provide an opportunity for DataArt employees to know queue size in DataArt Hub via PM
3
Choosing implementation method Create a service which takes an image from camera in DataArt Hub and performs image recognition Additional module makes decision about queue size based on recognition results It was recommended to implement Neural Network for image recognition because of following reasons: – We don’t need exact solution – Recognition error is not fatal – We have small amount (4) of possible queue states – Alternative solution (image analyzing with wavelets, analyzing pixels etc.) is too long and expensive to implement
4
Introducing Neural Networks computational model that is inspired by the structure and functional aspects of biological neural networks.
5
3 words about Neural Network structure
6
Neural Network Advantages – We program only structure of system, not behavior. Structure is universal Structure is flexible – We provide an image on the input and get recognition result on the output. Simple and fast recognition – We do not care about algorithm for image analyzing No need of PhD – We can reuse existing neural network in similar AND different tasks with minor changes Reusability – Parallel equations Fast & furious
7
How does it work Every 5 seconds image is downloaded from web
8
How does it work Image is converted to gray scale
9
How does it work Image is compressed, auto leveled and transformed to double array Auto leveling
10
How does it work Brightness adjustment Processed image is sent to input layer of network. If weights are correct on the output layer we get desired result (queue size). Weights
11
How does it work Threshold, integration Brightness adjustment Threshold value and integration of result are implemented Result picture are created
12
How does it work Threshold, integration Brightness adjustment Uploading results on server
13
Implementation details All Neural Network logic was placed in class library for reusability. This library can be used in other projects For monitoring network condition and making extra training if needed administrative tool was developed.
14
Administrative tool Creating and training network Retraining existing networks Enlarging training set Monitoring of correct work for all processes Monitoring current network error and dependability of recognition result. Saving and loading weights from file
15
Neural Network minuses Very careful approach to training set creation – Each pattern must be representative – Training set must cover all typical situations – large diversity of training for real-world operation We should always check what our network has learned Limited number of input, hidden and output nodes Large computations during training process
16
EXPLAINING PRINCIPLES OF NEURAL NETWORK Part 2
17
How does NN work?
18
Couple words about sigmoid function
19
Bias node No biasBias
20
NN Training Trial and error method – Initial weights have to be small enough – Feed with sample data set (training set) – Get the output value – Use error (output minus target value) as a criteria of success in the training algorithm – Change is small, number of iterations is big
21
Algorithm overview 1.Initialise the network with small random weights o maxWeight < 5.0 / (inputNodesNum * maxInputNodeValue) 2.Repeat for each input pattern in the input collection 1.Present an input pattern to the input layer of the network. 2.Get output values 3.Calculate network’s summary error 4.Reduce the error by changing NN weights properly (back propagation) 5.Propagate an error value back to each hidden neuron that is proportional to their contribution of the network’s activation error. 6.Adjust the weights feeding each hidden neuron to reduce their contribution of error for this input pattern. 3.Repeat step 2 until the network is suitably trained.
22
Back Propagation Is a way to reduce summary NN error and improve its performance “Blind paratrooper” method 3 steps: o
23
What can be customized in NN? Nodes number Network error Maximum number of training iterations Learning rate
24
Where NN has been used already Image/sound recognition Stock market Data classification Medicine Detecting credit card fraud. Forecast engines Geo routing systems Aviation NASA Etc
25
Questions
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.