VLSI IN NEURAL NETWORKS
Download as PPTX, PDF6 likes5,391 views
VLSI for neural networks and their applications was presented. Biological neural networks refer to networks of biological neurons that perform physiological functions. Artificial neural networks are mathematical models inspired by biological neural networks. Neural networks can be digital, analog, or hybrid and have applications in areas like pattern and speech recognition, economy, sociology, and basic sciences like investigating the impact of treatments over time. In conclusion, artificial neural networks that simulate human biological neurons have potential for wide implementation and can be trained on input data and then apply that knowledge to new cases.
VLSI IN NEURAL NETWORKS
- 1. VLSI FOR NEURAL NETWORKS AND THEIR APPLICATIONS PRESENTED BY: B.MOHAN KRISHNA J.MAHESH
- 2. OVERVIEW: The experiment What is Biological Neural Network? What is Artificial Neural Network? Types of Neural networks Applications Conclusion
- 6. Pigeons were able to discriminate between Van Gogh and Chagall with 95% accuracy (when presented with pictures they had been trained on) Discrimination still 85% successful for previously unseen paintings of the artists Results:
- 7. Biological Neural Network: The term neural network was traditionally used to refer to a plexus or circuit of biological neurons. They are often identified as groups of neurons that perform a specific physiological function in laboratory analysis.
- 8. Artificial Neural Network: It is a mathematical model inspired by biological neural networks.
- 9. The neural network is divided into three different categories : Digital Analog Hybrid
- 10. DIGITAL: Encompasses many sub-categories including slice architectures and RBF architectures. Two architectures namely single instruction with multiple data (SIMD) and systolic arrays are also used.
- 11. Analog: Analog hardware networks can exploit physical properties to do network operations and thereby obtain high speed and densities. The first analog commercial chip was the Intel 80170NW ETANN (ElectricallyTrainable Analog Neural Network) that contains 64 neurons and 10280 weights.
- 12. Hybrid: Hybrid designs attempt to combine the best of analog and digital techniques. The external inputs/outputs are digital to facilitate integration into digital systems.
- 13. Applications: Economy, speech and patterns recognition, sociology, etc. Face recognition, character recognition Voice recognition In basic sciences
- 14. Example: Voice Recognition Task: Learn to discriminate between two different voices saying “Hello” Data Sources Steve David Format Frequency distribution
- 15. Applications in Clinical Medicine Patient who hospitalize for having high-risk diseases required special monitoring as the disease might spread in no time. They indicate that Neural Network predict the patients’ survival and death very well compared to the surgeons.
- 16. Applications in Basic sciences: In basic sciences, Neural Network helps clinician to investigate the impact of parameter after certain conditions or treatments. Example:Learning the time course of blood glucose
- 17. The brain, neural networks and computers: Historically the brain has been viewed as a type of computer ,vice versa. Computers do not provide us with accurate hardware for describing the brain. Neural networks are used in artificial intelligence.
- 18. Conclusion: Neural Network which simulates the function of human biological neuron, has potential of ease implementation in many applications . The main consideration of Neural Network implementation is the input data. Once the network is train, the knowledge could be applied to all cases including the new cases in the domain.