Such a framework: memory-driven computing accelerators. Follow:
Hu et al., " Dot-Product Engine for Neuromorphic Computing: Programming 1T1M Crossbar to Accelerate Matrix-Vector Multiplication ", 2016 - https://www.labs.hpe.com/techreports/2016/HPE-2016-23.pdf
Beausoleil et al., " Beyond the qubit: quantum computing, practical alternatives, and Memory-Driven Computing ", 2019 - https://h20195.www2.hpe.com/v2/Getdocument.aspx?docname=a00061878enw&skiphtml=1
See the following link for a recent review on "FPGA-based Accelerators of Deep Learning Networks for Learning and Classification" - it might be of interest: https://arxiv.org/pdf/1901.00121.pdf
DNNs (Deep Neural Networks) have numerous applications such as image classification, speech recognition, video analysis, see the following link http://www.arxiv-sanity.com/1611.02120