1.58-b FeFET-Based Ternary Neural Networks: Achieving Robust Compute-In-Memory With Weight-Input Transformations

Exploring foci of: IEEE Journal on Exploratory Solid-State Computational Devices and Circuits • Vol 11 1.58-b FeFET-Based Ternary Neural Networks: Achieving Robust Compute-In-Memory With Weight-Input Transformations January 2025 • Imtiaz Ahmed, Akul Malhotra, Revanth Koduru, Sumeet Kumar Gupta Ternary weight neural networks (TWNs), with weights quantized to three states (&#x2212;1, 0, and 1), have emerged as promising solutions for resource-constrained edge artificial intelligence (AI) platforms due to their high energy efficiency with acceptable inference accuracy. Further energy savings can be achieved with TWN accelerators utilizing techniques such as compute-in-memory (CiM) and scalable technologies such as ferroelectric transistors (FeFETs). Although the standard 1T-FeFET CiM design offers high den… Open Article Page

Neural Correlates Of Consciousness News 12 Networks Convolutional Neural Network Recurrent Neural Network Palo Alto Networks Rectifier (Neural Networks) Physics-Informed Neural Networks Paramount Media Networks Neural Oscillation Open Article

Residual Neural Network Feedforward Neural Network Spice Networks Juniper Networks Modularity (Networks) The Wealth Of Networks F5 Networks Neural Circuit Neural Tube Open Article

Fox Sports Networks Extreme Networks Open Article