Single transistor learning synapse with long term storage

@article{Hasler1995SingleTL,
  title={Single transistor learning synapse with long term storage},
  author={Paul E. Hasler and Chris Diorio and Bradley A. Minch and Carver Mead},
  journal={Proceedings of ISCAS'95 - International Symposium on Circuits and Systems},
  year={1995},
  volume={3},
  pages={1660-1663 vol.3}
}
  • P. Hasler, C. Diorio, +1 author C. Mead
  • Published 28 April 1995
  • Physics, Computer Science
  • Proceedings of ISCAS'95 - International Symposium on Circuits and Systems
We describe the design, fabrication, characterization, and modeling of an array of single transistor synapses. The single transistor synapses simultaneously perform long term weight storage, compute the product of the input and floating gate value, and update the weight value according to a hebbian or a backpropagation learning rule. The charge on the floating gate is decreased by hot electron injection with high selectivity for a particular synapse. The charge on the floating gate is increased… 
A single-transistor silicon synapse
TLDR
A new floating-gate silicon MOS transistor for analog learning applications is developed, and a memory-update rule is derived from the physics of the tunneling and injection processes to permit the development of dense, low-power silicon learning systems.
A floating-gate MOS learning array with locally computed weight updates
We have demonstrated on-chip learning in an array of floating-gate MOS synapse transistors. The array comprises one synapse transistor at each node, and normalization circuitry at the row boundaries.
A Complementary Pair of Four-Terminal Silicon Synapses
We have developed a complementary pair of pFETand nFET floating-gate silicon MOS transistors foranalog learning applications. The memory storage is nonvolatile;hot-electron injection and electron
Compact floating-gate learning array with STDP
TLDR
A Spiking Neural Network (SNN) architecture that incorporates Integrate-and-fire type neurons and floating-gate transistors (FGTs) to store the synaptic weights to achieve robust off-chip communication is presented.
Floating-gate MOS synapse transistors
TLDR
This work proposes a simple circuit element combining nonvolatile analog memory storage with locally computed memory updates that can be integrated into silicon learning systems.
An analog floating-gate node for Supervised learning
  • P. Hasler, J. Dugger
  • Computer Science
    IEEE Transactions on Circuits and Systems I: Regular Papers
  • 2005
TLDR
An improved analog floating-gate pFET synapse is presented that implements a supervised learning algorithm similar to the least mean square (LMS) learning rule that will enable larger-scale, on-chip learning networks than previously possible.
Synaptic plasticity in VLSI : a floating-gate approach
One of the major areas of research by neurobiologists is long term synaptic modification or plasticity of synapses. Synapses are the interconnections between neurons. Each synapse is associated with
Correlation learning rule in floating-gate pFET synapses
  • P. Hasler, J. Dugger
  • Physics, Computer Science
    ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349)
  • 1999
TLDR
The weight dynamics of the floating-gate pFET synapse are studied and a weight update rule is derived such that the equilibrium weight value is proportional to the correlation between the gate and drain voltages.
Correlation learning rule in floating-gate pFET synapses
We study the weight dynamics of the floating-gate pFET synapse and the effects of the pFET's gate and drain voltages on these dynamics. We show that we can derive a weight update rule such that the
A Learning-Enabled Neuron Array IC Based Upon Transistor Channel Models of Biological Phenomena
TLDR
A single-chip array of 100 biologically-based electronic neuron models interconnected to each other and the outside environment through 30,000 synapses is presented, using Address-Event Representation (AER) spike communication for inputs and outputs to this IC.
...
1
2
3
4
5
...

References

SHOWING 1-5 OF 5 REFERENCES
Single Transistor Learning Synapses
TLDR
The design, fabrication, characterization, and modeling of an array of single transistor synapses that compute, learn, and provide non-volatile memory retention are described.
Fowler‐Nordheim Tunneling into Thermally Grown SiO2
Electronic conduction in thermally grown SiO2 has been shown to be limited by Fowler‐Nordheim emission, i.e., tunneling of electrons from the vicinity of the electrode Fermi level through the
Sin- gle Transistor Learning Synapses", Advances in Neu- ral Information Processing Systems 7, Morgan Kauf- mann Publishers
  • San Mateo, CA,
  • 1995
An Analytic model of Hot Electron Injection from Boltzman Transport
  • Tech. Report
  • 1234