Analog Resistive Switching Devices for Training Deep Neural Networks with the Novel Tiki-Taka Algorithm.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 38205713.
- Also identified by DOI 10.1021/acs.nanolett.3c03697 and PMC identifier 10811689.
- Licence recorded as CC BY.
- The licence permits redistribution, so the abstract is shown in full and the full text is available from the publisher.
Abstract
A critical bottleneck for the training of large neural networks (NNs) is communication with off-chip memory. A promising mitigation effort consists of integrating crossbar arrays of analogue memories in the Back-End-Of-Line, to store the NN parameters and efficiently perform the required synaptic operations. The "<i>Tiki-Taka</i>" algorithm was developed to facilitate NN training in the presence of device nonidealities. However, so far, a resistive switching device exhibiting all the fundamental Tiki-Taka requirements, which are many programmable states, a centered <i>symmetry point</i>, and low programming noise, was not yet demonstrated. Here, a complementary metal-oxide semiconductor (CMOS)-compatible resistive random access memory (RRAM), showing more than 30 programmable states with low noise and a symmetry point with only 5% skew from the center, is presented for the first time. These results enable generalization of Tiki-Taka training from small fully connected networks to larger long-/short-term-memory types of NN.