Related Experiment Videos
Quantization effects in digitally behaving circuit implementations of Kohonen networks.
IEEE Transactions on Neural Networks
|January 1, 1994
Summary
Quantization in neural networks impacts Kohonen
Area of Science:
- Artificial Intelligence
- Computer Engineering
- Neuroscience
Background:
- Implementing neural networks on hardware involves synaptic weight quantization.
- Kohonen's self-organizing maps are a type of neural network susceptible to quantization effects.
Purpose of the Study:
- To analyze the impact of synaptic weight quantization on Kohonen's self-organizing maps.
- To determine optimal network parameters for quantized implementations.
- To present a hardware-efficient analog network design.
Main Methods:
- Qualitative analysis of quantization effects on network convergence and properties.
- Parameter selection based on analytical insights.
- Design and implementation of an analog nonlinear network using CMOS technology.
Main Results:
- Spatially decreasing neighborhood functions are superior to rectangular ones for quantized Kohonen maps.
- Established guidelines for selecting adaptation gain and neighborhood parameters.
- Demonstrated a functional analog network suitable for mixed-signal applications.
Conclusions:
- Quantization necessitates careful parameter tuning in self-organizing maps.
- Spatially decreasing neighborhoods mitigate quantization errors effectively.
- The presented analog network offers a viable solution for efficient hardware implementation of Kohonen maps.
Related Concept Videos
01:25Network Function of a Circuit
Frequency response analysis in electrical circuits provides vital insights into a circuit's behavior as the frequency of the input signal changes. The transfer function, a mathematical tool, is instrumental in understanding this behavior. It defines the relationship between phasor output and input and comes in four types: voltage gain, current gain, transfer impedance, and transfer admittance. The critical components of the transfer function are the poles and zeros.
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...
01:13Integrator and Differentiator
Op-amp circuits have significant applications in various fields, including automotive engineering. One such application is cruise control systems in cars, where op-amp circuits are integral for maintaining a constant speed. In these systems, op-amps function as both integrators and differentiators.
An integrator within an op-amp circuit produces an output directly proportional to the integral of the input signal. This is achieved by replacing the feedback resistor in a typical inverting...
An integrator within an op-amp circuit produces an output directly proportional to the integral of the input signal. This is achieved by replacing the feedback resistor in a typical inverting...
01:19The Role of Ion Channels in Neuronal Computation
A postsynaptic neuron usually receives numerous impulses from several other presynaptic neurons. The axon hillock of the postsynaptic neuron integrates all these signals and determines the likelihood of firing an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential.
01:20Design Example: Capacitance Multiplier Circuit
In integrated circuit technology, a capacitance multiplier is often utilized to produce a larger capacitance value when a small physical capacitance falls short. This is achieved by a circuit that multiplies capacitance values by a factor of up to 1000, such that a 10-pF capacitor can replicate the performance of a 100-nF capacitor.
The circuit illustrated in Figure 1 below incorporates two op-amps, with the first operating as a voltage follower and the second acting as an inverting amplifier.
The circuit illustrated in Figure 1 below incorporates two op-amps, with the first operating as a voltage follower and the second acting as an inverting amplifier.
01:24Convolution: Math, Graphics, and Discrete Signals
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...