Related Experiment Videos
Analog CMOS implementation of a multilayer perceptron with nonlinear synapses
1Electron. Lab., Swiss Federal Inst. of Technol., Zurich.
IEEE Transactions on Neural Networks
|January 1, 1992
Summary
A novel neurocomputer chip utilizing analog integrated circuits and CMOS technology has been developed. This compact chip efficiently processes information using 18 neurons and 161 synapses, demonstrating a new approach to artificial intelligence hardware.
Area of Science:
- Neurocomputing and Artificial Intelligence Hardware
- Analog Integrated Circuit Design
- Complementary Metal-Oxide-Semiconductor (CMOS) Technology
Background:
- Advancements in artificial intelligence necessitate efficient hardware for neural network computation.
- Analog integrated circuits offer potential for low-power, high-density neural network implementation.
- Existing neurocomputer designs face challenges in scalability and synapse non-linearity.
Purpose of the Study:
- To design and fabricate a high-density analog neurocomputer chip.
- To implement and analyze the error back-propagation algorithm for analog synapse utilization.
- To investigate the impact of synapse offset voltages on circuit performance.
Main Methods:
- Development of a neurocomputer chip using 3 µm CMOS technology.
- Integration of 18 neurons and 161 synapses within a compact 1.6 mmx2.4 mm area.
- Formalization of the error back-propagation algorithm adapted for nonlinear synapses and analysis of offset voltage effects.
Main Results:
- Successful fabrication of a functional neurocomputer chip with 16 inputs and 4 outputs.
- Demonstration of weight storage using synapse storage capacitors.
- Analysis of synapse offset voltage influence on overall circuit performance.
Conclusions:
- The developed analog neurocomputer chip represents a significant step towards efficient AI hardware.
- The formalized error back-propagation algorithm enables the use of small, nonlinear synapses.
- Further research can optimize synapse design to mitigate offset voltage effects for improved performance.
Related Concept Videos
01:25Neural Circuits
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
01:22Multi-input and Multi-variable systems
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
In the absence of...
01:25MOS Capacitor
A Metal-Oxide-Semiconductor (MOS) capacitor is a fundamental structure used extensively in semiconductor device technology, particularly in the fabrication of integrated circuits and MOSFETs (metal-oxide-semiconductor field-effect transistors). The MOS capacitor consists of three layers: a metal gate, a dielectric oxide, and a semiconductor substrate.
The metal gate is typically made from highly conductive materials such as aluminum or polysilicon. Beneath the metal gate lies a thin layer of...
The metal gate is typically made from highly conductive materials such as aluminum or polysilicon. Beneath the metal gate lies a thin layer of...
01:26Linear Approximation in Frequency Domain
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear.
01:26Classification of Systems-I
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
01:20Inverting and Non-inverting OpAmps
In an inverting amplifier, the input voltage is connected through a resistor to the inverting terminal. Meanwhile, the non-inverting terminal is grounded and a feedback resistor is established between the inverting and output terminal, as depicted in Figure 1.