Alert button
Picture for Khaled Nabil Salama

Khaled Nabil Salama

Alert button

Towards Efficient In-memory Computing Hardware for Quantized Neural Networks: State-of-the-art, Open Challenges and Perspectives

Add code
Bookmark button
Alert button
Jul 08, 2023
Olga Krestinskaya, Li Zhang, Khaled Nabil Salama

The amount of data processed in the cloud, the development of Internet-of-Things (IoT) applications, and growing data privacy concerns force the transition from cloud-based to edge-based processing. Limited energy and computational resources on edge push the transition from traditional von Neumann architectures to In-memory Computing (IMC), especially for machine learning and neural network applications. Network compression techniques are applied to implement a neural network on limited hardware resources. Quantization is one of the most efficient network compression techniques allowing to reduce the memory footprint, latency, and energy consumption. This paper provides a comprehensive review of IMC-based Quantized Neural Networks (QNN) and links software-based quantization approaches to IMC hardware implementation. Moreover, open challenges, QNN design requirements, recommendations, and perspectives along with an IMC-based QNN hardware roadmap are provided.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

Learning in Memristive Neural Network Architectures using Analog Backpropagation Circuits

Add code
Bookmark button
Alert button
Aug 31, 2018
Olga Krestinskaya, Khaled Nabil Salama, Alex Pappachen James

Figure 1 for Learning in Memristive Neural Network Architectures using Analog Backpropagation Circuits
Figure 2 for Learning in Memristive Neural Network Architectures using Analog Backpropagation Circuits
Figure 3 for Learning in Memristive Neural Network Architectures using Analog Backpropagation Circuits
Figure 4 for Learning in Memristive Neural Network Architectures using Analog Backpropagation Circuits

The on-chip implementation of learning algorithms would speed-up the training of neural networks in crossbar arrays. The circuit level design and implementation of backpropagation algorithm using gradient descent operation for neural network architectures is an open problem. In this paper, we proposed the analog backpropagation learning circuits for various memristive learning architectures, such as Deep Neural Network (DNN), Binary Neural Network (BNN), Multiple Neural Network (MNN), Hierarchical Temporal Memory (HTM) and Long-Short Term Memory (LSTM). The circuit design and verification is done using TSMC 180nm CMOS process models, and TiO2 based memristor models. The application level validations of the system are done using XOR problem, MNIST character and Yale face image databases

* IEEE Transactions on Circuits and Systems 1: Regular Papers, 2018  
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon