English
CEA-Leti Builds Fully Integrated Bio-Inspired Neural Network with RRAM-Based Synapses & Analogue Spiking Neurons
Functionality of Circuit Presented at IEDM 2019 Was Demonstrated With Handwritten Digits Classification on a Tablet Screen
SAN FRANCISCO – Dec. 13, 2019 – Leti, a technology research institute of CEA Tech, has fabricated a fully integrated bio-inspired neural network, combining resistive-RAM-based synapses and analog spiking neurons. The functionality of this proof-of-concept circuit was demonstrated thanks to handwritten digits classification.
Resistive-RAM (RRAM) is a type of non-volatile random-access computer memory that works by changing the resistance across a dielectric solid-state material.
The research work presented at IEDM 2019 measured a 5x reduction in energy use compared to an equivalent chip using formal coding. The neural network implementation is made such that synapses are placed close to neurons, which enables direct synaptic current integration.
"The entire network is integrated on-chip," said Alexandre Valentian, lead author of the paper, "Fully Integrated Spiking Neural Network with Analog Neurons and RRAM Synapses". "No part is emulated or replaced by an external circuit, as in some other projects. It even was used in a live demo where users could draw digits with their finger on a tablet and it is classified after conversion into a spike train."
Spiking neural networks, also known as third-generation neural networks, are composed of bio-inspired neurons, which communicate by emitting spikes, discrete events that take place at a point in time, rather than continuous values. These networks promise to further reduce required computational power because they use less complex computing operations, e.g. additions instead of multiplications. They also inherently exploit sparsity of input events, since they are intrinsically event-based.
"To date, demonstrations of RRAM-based SNNs have been limited to system-level simulations calibrated on experimental data," the IEDM paper explains. "In this paper, we present for the first time a complete integration of a SNN combining analog neurons and RRAM synapses."
1. Demonstration of live handwritten digits classification
The paper explains that "the test chip, fabricated in 130nm CMOS, shows well-controlled integration of synaptic currents and no RRAM read-disturb issue during inference tasks (at least 750M spikes)."
"Data-centric workloads exhibited by Deep Neural Network (DNN) applications call for circuit architectures where data movement is reduced to a minimum," the paper says. "This has motivated architectures in which memories are spatially located near the computing elements. These memories must be very dense, preferably non-volatile and inserted into the computational dataflow, therefore RRAMs are excellent candidates to this purpose."
The study, which was supported by CEA-List, underscores CEA-Leti's expertise at manufacturing RRAM memories on top of CMOS wafers.
2. SEM cross-section of the RRAM cell monolithically integrated on the top of 130nm CMOS
|
||||||
Related News
- CEA-Leti Paper in Nature Communications Reports First Complete Memristor-Based Bayesian Neural Network Implementation For Real-World Task
- CEA-LETI Develops Circuits for Neuromorphic Processors That Replace CMOS Transistor-Based Tcam Memory With Rram-Based Tcam Memory
- Renesas tapes out spiking neural network chip
- Imec Builds World's First Spiking Neural Network-Based Chip for Radar Signal Processing
- Xilinx and Mipsology Release Integrated Solution for High-Performance Inference in Data Center
Breaking News
- Ubitium Debuts First Universal RISC-V Processor to Enable AI at No Additional Cost, as It Raises $3.7M
- TSMC drives A16, 3D process technology
- Frontgrade Gaisler Unveils GR716B, a New Standard in Space-Grade Microcontrollers
- Blueshift Memory launches BlueFive processor, accelerating computation by up to 50 times and saving up to 65% energy
- Eliyan Ports Industry's Highest Performing PHY to Samsung Foundry SF4X Process Node, Achieving up to 40 Gbps Bandwidth at Unprecedented Power Levels with UCIe-Compliant Chiplet Interconnect Technology
Most Popular
- Cadence Unveils Arm-Based System Chiplet
- CXL Fabless Startup Panmnesia Secures Over $60M in Series A Funding, Aiming to Lead the CXL Switch Silicon Chip and CXL IP
- Esperanto Technologies and NEC Cooperate on Initiative to Advance Next Generation RISC-V Chips and Software Solutions for HPC
- Eliyan Ports Industry's Highest Performing PHY to Samsung Foundry SF4X Process Node, Achieving up to 40 Gbps Bandwidth at Unprecedented Power Levels with UCIe-Compliant Chiplet Interconnect Technology
- Arteris Selected by GigaDevice for Development in Next-Generation Automotive SoC With Enhanced FuSa Standards
|
E-mail This Article | 
|
|
Printer-Friendly Page |