Search Results - compute-in-memory

3 Results Sort By:
Accurate Compute-In-Memory Accelerator With Multi-Level Analog Weight Storage (Case No. 2026-169)
Summary: UCLA researchers in the Department of Electrical and Computer Engineering have developed a high-density, multi-level CTT-based compute-in-memory architecture that enables precise, energy-efficient analog computation directly within memory for high-performance computing. Background: Conventional digital processors for artificial intelligence...
Published: 6/3/2026   |   Updated: 6/3/2026   |   Inventor(s): Sudhakar Pamarti, Mohammadreza Zeinali, Samyak Chakrabarty, Vinod Kurian Jacob
Keywords(s): Advanced Computing / AI, advanced computing methods, AI, AI hardware, analog computing, Artificial Intelligence, artificial intelligence accelerators, Artificial Neural Network, CMOS, compute-in-memory, edge computing, Energy Efficiency, high-performance computing, Memory, parallel computing, Transistor, transistors
Category(s): Software & Algorithms > Artificial Intelligence & Machine Learning, Electrical, Electrical > Computing Hardware, Electrical > Electronics & Semiconductors, Electrical > Electronics & Semiconductors > Circuits, Electrical > Electronics & Semiconductors > Memory
Calibration of Analog Multi-Bit Storage Elements Without Off-Chip Components (Case No. 2026-167)
Summary: UCLA researchers in the Department of Electrical and Computer Engineering have developed a scalable, energy-efficient technique for high-precision threshold voltage tuning and verification in charge trap transistor arrays using low-overhead on-chip measurement. Background: Charge trap transistors (CTTs) enable non-volatile analog multi-bit...
Published: 6/3/2026   |   Updated: 6/3/2026   |   Inventor(s): Sudhakar Pamarti, Mohammadreza Zeinali
Keywords(s): analog computing, CMOS, compute-in-memory, Electrical, Electrical Engineering, Integrated Circuit, large-area arrays, low latency computing, Memory, Network Analysis (Electrical Circuits), Neuromorphic circuits, programming, pulsed load modulation, scalable fabrication, soft electrical circuits
Category(s): Electrical, Electrical > Computing Hardware, Energy & Environment, Energy & Environment > Energy Efficiency, Electrical > Electronics & Semiconductors > Circuits, Electrical > Electronics & Semiconductors
Event-Driven Integrate and Fire (EIF) Neuron Circuit for Neuromorphic Computing System (Case No. 2024-275)
Summary: Researchers in the UCLA Department of Electrical and Computer Engineering have developed an energy efficient neuromorphic computing architecture. Background: Widespread growth in demand for artificial intelligence systems has highlighted limitations in current central processing unit (CPU) designs, particularly in terms of energy efficiency...
Published: 11/18/2025   |   Updated: 2/4/2025   |   Inventor(s): Mau-Chung Chang, Chao Jen Tien, Yong Hei
Keywords(s): Advanced Computing / AI, advanced computing methods, AI hardware, analog computing, Artifical Intelligence (Machine Learning, Data Mining), artificial electromagnetic materials, Artificial Intelligence, artificial intelligence algorithms, artificial intelligence augmentation, artificial intelligence/machine learning models, artificial intelligence-generated content, Artificial Neural Network, Artificial Neural Network Artificial Neuron, artificial presenting cells, artificial-intelligent materials, Cloud Computing, computational efficiency, computational imaging, compute-in-memory, Computer Aided Learning, Computer Architecture, Computer Monitor, Computer Vision, CPU design, deep neural networks (DNN), Energy Density, Energy Efficiency, event-driven processing, generative artificial intelligence, latency encoding, low latency computing, low-power architecture, matrix multiplication, Medical artificial intelligence (AI), Neuromorphic computing, offline learning, online learning, spike neural networks (SNN), Supercomputer
Category(s): Electrical, Electrical > Signal Processing, Electrical > Electronics & Semiconductors, Electrical > Computing Hardware, Software & Algorithms, Software & Algorithms > Artificial Intelligence & Machine Learning