Related Experiment Video
Updated: Jan 25, 2026
11:18
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
10.8K
A Soft-Pruning Method Applied During Training of Spiking Neural Networks for In-memory Computing Applications
Yuhan Shi1, Leon Nguyen1, Sangheon Oh1
1Electrical and Computer Engineering Department, University of California, San Diego, San Diego, CA, United States.
Frontiers in Neuroscience
|May 14, 2019
Summary
We developed a novel pruning method for spiking neural networks (SNNs) that enhances energy efficiency during online learning on emerging non-volatile memory (eNVM) devices. This method significantly reduces network updates while maintaining high classification accuracy.
Area of Science:
- Neuroscience
- Computer Science
- Materials Science
Background:
- Spiking neural networks (SNNs) mimic biological brains for efficient computation.
- Emerging non-volatile memory (eNVM) offers in-memory computing potential for SNNs.
- Online learning in SNNs requires significant energy, limiting low-power applications.
Purpose of the Study:
- To improve the energy efficiency of online learning in SNNs using eNVM devices.
- To introduce a novel, training-integrated pruning method for SNNs.
- To reduce unnecessary parameter updates during SNN training.
Main Methods:
- Developed a pruning algorithm for SNNs based on neuron output firing characteristics.
- Integrated the pruning method during the SNN training phase.
- Evaluated the SNN and pruning scheme on the MNIST dataset using eNVM technology.
Main Results:
- Achieved ~90% classification accuracy on MNIST with up to ~75% network pruning.
- Significantly reduced the number of weight updates during training.
- Demonstrated complementary energy efficiency gains with eNVM platforms.
Conclusions:
- The proposed pruning method enhances energy efficiency for SNN online learning on eNVM.
- This approach enables efficient, neuro-inspired systems for low-power applications.
- Algorithmic optimization is key to unlocking the potential of eNVM for SNNs.
Related Concept Videos
02:26Protein Networks
4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
02:18Network Covalent Solids
16.1K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.1K
01:24Area Computation by the Alternative Coordinate Method
577
The alternative coordinate method, also known as the Shoelace Formula, is a technique for determining the area of a traverse using Cartesian coordinates. This method relies on the sequential arrangement of x and y coordinates for each point of the shape, ensuring accuracy and ease of application.In this approach, each corner's x and y coordinates are listed as fractions, with the x-coordinate as the numerator and the y-coordinate as the denominator. These coordinates are arranged sequentially...
577
01:23System of Memory
7.3K
Memory is categorized into three major systems: sensory memory, short-term memory (STM), and long-term memory (LTM). These systems differ in their capacity and the duration for which they can hold information. Sensory memory captures raw sensory input from the environment, holding it for just a few seconds or less. For example, on hearing a brief, loud sound, like a car horn honking, the sound seems to linger in the mind for a moment even after it stops. This is an instance of sensory memory...
7.3K
01:24Working Memory
841
Working memory refers to a combination of components, including short-term memory and attention, that allow an individual to hold information temporarily as we perform cognitive tasks. It is an essential cognitive function that enables the execution of complex tasks such as problem-solving, comprehension, and reasoning. Unlike short-term memory, which simply involves the storage of information for a brief period, working memory involves the active manipulation and processing of this...
841
01:18Long-Term Memory
664
Long-term memory is a relatively permanent type of memory, capable of storing vast amounts of information over extended periods. Its storage capacity is generally considered unlimited.
Long-term memory can be categorized into two primary types: explicit and implicit memory. Explicit memory, also known as declarative memory, involves the conscious recollection of information that we deliberately try to remember, recall, and articulate. This type of memory encompasses specific facts, events, and...
Long-term memory can be categorized into two primary types: explicit and implicit memory. Explicit memory, also known as declarative memory, involves the conscious recollection of information that we deliberately try to remember, recall, and articulate. This type of memory encompasses specific facts, events, and...
664