Artificial neural network
- 1. ARTIFICIAL NEURAL NETWORK SUBMITTED BY: GAURAV PANDEY
- 2. OUTLINE ARTIFICIALNEURAL NETWORK 03 01 04 02 ARTIFICIALNEURAL NETWORK 07 05 08 06 WHAT IS ANN? ARCHITECTURE ALGORITHMS APPLICATIONS ADVANTAGES/ DISADVANTAGES WHY USE ANN? WORKING PERCEPTRON
- 3. What is ANN ? ANN stand for Artificial Neural Network. - an information processing paradigm inspired by an Human nervous system . - Composed of large number of highly interconnected processing elements (neurons). - The ability to learn from experience in order to improve their performance. - Similar to biological system ANN also involves synaptic connections between neurons.
- 4. Why use ANN ? - Knowledge acquisition under noise and uncertainty. - ability to derive meaning from complicated or imprecise data. - extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. - Adaptive learning and fault tolerance. - Flexible Knowledge representation. - Efficient knowledge processing.
- 5. The Architecture of Neural Network Feed forward Neural Network This neural network is one of the simplest for of ANN, where the data or the input travels in one direction. The data passes through the input nodes and exit on the output nodes.
- 6. The Architecture of Neural Network Radial basis function Neural Network
- 7. The Architecture of Neural Network Kohonen Self Organizing Neural Network The objective of a Kohonen map is to input vectors of arbitrary dimension to discrete map comprised of neurons. The map needs to be trained to create its own organization of the training data. It comprises of either one or two dimensions.
- 8. The Architecture of Neural Network Recurrent Neural Network The Recurrent Neural Network works on the principle of saving the output of a layer and feeding this back to the input to help in predicting the outcome of the layer.
- 9. The Perceptron The most basic form of an activation function is a simple binary function that has only two possible results. The Heaviside Step function. This function returns 1 if the input is positive or zero, and 0 for any negative input. A neuron whose activation function is a function like this is called a Perceptron.
- 10. WORKING OF NEURAL NETWORK. INPUT LAYER HIDDEN LAYER OUTPUT LAYER INPUTS OUTPUT
- 11. Neural Network Learning Algorithms Supervised Learning Reinforced Learning Unsupervised Learning Supervised learning is a learning in which we teach or train the machine using data which is well labeled that means some data is already tagged with correct answer. After that, machine is provided with new set of examples(data) so that supervised learning algorithm analyses the training data(set of training examples) and produces an correct outcome from labeled data. Reinforcement learning is a type of dynamic programming that trains algorithms using a system of reward and punishment. A reinforcement learning algorithm, or agent, learns by interacting with its environment. The agent receives rewards by performing correctly and penalties for performing incorrectly. The agent learns without intervention from a human by maximizing its reward and minimizing its Unsupervised learning is the training of machine using information that is neither classified nor labeled and allowing the algorithm to act on that information without guidance. Here the task of machine is to group unsorted information according to similarities, patterns and differences without any prior training of data.
- 12. APPLICATION OF NEURAL NETWORK Pattern recognition. Medical Field. Control system and monitoring. Forecasting – sales, market research, meteorology. Marketing and financial application. Robotics, Facial animation , Event prediction. Signal Filtering (reduction of radio noise). Adaptive Control (vehicle Guidance).
- 13. ADVANTAGES A neural network can perform a task that a linear program cannot. When an element of the neural network fails, it can continue without any problem by their parallel nature. A neural network learns and does not need to be reprogrammed. It can be implemented in any applications. They can perform associative memory (associative - like working memory in humans) as opposed to addressable memory (typical for classical computers). They do not require knowledge of the algorithm solving the problem (automatic learning).
- 14. DIS-ADVANTAGES The neural network needs training to operate. The architecture of a neural network is different from the architecture of microprocessors therefore needs to be emulated. Requires high processing time for large neural networks. : There are many parameters to be set in a neural network and optimizing the network can be challenging, especially to avoid overtraining. Require high processing time for large neural networks.
- 15. Modeling and Diagnosing the Cardiovascular System Neural Networks are used experimentally to model the human cardiovascular system. Diagnosis can be achieved by building a model of the cardiovascular system of an individual and comparing it with the real time physiological measurements taken from the patient. If this routine is carried out regularly, potential harmful medical conditions can be detected at an early stage and thus make the process of combating the disease much easier. A model of an individual's cardiovascular system must mimic the relationship among physiological variables (i.e., heart rate, systolic and diastolic blood pressures, and breathing rate) at different physical activity levels. If a model is adapted to an individual, then it becomes a model of the physical condition of that individual. The simulator will have to be able to adapt to the features of any individual without the supervision of an expert.
- 16. CONCLUSION A Neural Network can be successfully used in the project, given that we have access to enough training data. Since we need it to be highly accurate, we need to carefully gather contextual variables that closely relate to diagnosing heart murmur and its various grades.
- 17. REFERENCES • Siewnicka A., Janiszowski K., Gawlikowski M. (2014) “A Physical Model of the Human Circulatory System for the Modeling, Control and Diagnostic of Cardiac Support Processes”. In: Březina T., Jabloński R. (eds) Mechatronics 2013. Springer, Cham, 978-3-319-02294-9_104. • Ferrari, G., Kozarski, M., De Lazzari, C., Gorczynska, K., Mimmo, R., Guaragno, M., Darowski, M.: “Modelling of cardiovascular system: development of a hybrid (numerical-physical) model”. International Journal of Artificial Organs 26(12), 1104–1114 (2003). • The Perceptron https://appliedgo.net/perceptron/accessed on 21/04/2018 at 22:00 • Types of neural network https://analyticsindiamag.com/6-types-of-artificial- neural-networks-currently-being-used-in-todays-technology/ accessed on 21/04/2018 at 22:10 • Artificial Neural Network https://data-flair.training/artificial-neural-network- applications/ accessed on 22/04/2018 at 20:50
- 18. THANK YOU!!