Learn more about UC TechAlerts – Subscribe to categories and get notified of new UC technologies

Browse Category: Computer > Hardware

Categories

[Search within category]

Fast Deep Neural Network (DNN) Training/Execution on Hardware Platforms

With the growing range of applications for Deep Neural Networks (DNNs), the demand for higher accuracy has directly impacted the depth of the state-of-the-art models. Although deeper networks are shown to have higher accuracy, they suffer from drastically long training time and slow convergence speed with high computational complexity.

Stream-Based Memory Access Specialization For General Purpose Processors

Researchers led by Zhengrong Wang and Tony Nowatzki from the Computer Science Department at UCLA have created a way to improve computer processing power, speed, and efficiency by optimizing how processors access memory.

Lambda-Reservoir Computing

UCLA researchers in the Department of Electrical and Computer Engineering have developed a Spectral Reservoir Computer that processes data using nonlinear optical interactions.

Time-Domain Mixed-Signal Vector-By-Matrix Multiplier

A time-domain mixed-signal VMM exploiting a modified configuration of 1 MOSFET-1 RRAM (1T-1R) array.

Versatile Stochastic Dot- Product Circuit

A compact, fast, energy-efficient, and scalable stochastic dot-product circuit.

Method and Apparatus for Movement Therapy Gaming System

Rehabilitation therapy, while an important tool for the long term recovery of patients affected by brain injury or disease, is expensive and requires one-on-one attention from a certified healthcare professional. UCI researchers have developed a computer-based system that provides arm movement therapy for patients. The system allows patients to independently practice hand and arm movements, improving therapeutic outcomes, while reducing hospital visits and cost for both patients and healthcare providers.

Advanced Power Management IC’s for Li-Ion Powered Mobile & IoT Devices

Most modern mobile, wearable, and Internet of Things (IoT) devices utilize Li-ion batteries as power supplies. Since the 2.8-4.2V Li-ion output voltage range is not compatible with the 0.6-1.0V voltage requirements of most system-on-chips (SoCs) implemented in scaled CMOS, a DC-DC converter, typically implemented as a discrete power management integrated circuit (PMIC), is placed between the battery and the load.

Cloud- enabled Wireless pH Monitoring in Laboratory Sample Vials

A team of inventors at UCI have developed a miniaturized, wireless pH sensing system capable of monitoring the pH of laboratory samples in real-time with cloud-enabled connections for data collection. The sensor is designed to fit into the caps of standard sample vials, providing continuous measurements and eliminating the need to open vials during sensing.

Magnetic Memory Bits with Perpendicular Magnetization Switched By Current-Induced Spin-Orbit Torques

UCLA researchers in the Department of Electrical and Computer Engineering have developed a novel spin-orbit-torque (SOT)-controlled magnetic random access memory driven by in-plane currents.

Techniques for Creation and Insertion of Test Points for Malicious Circuitry Detection

Researchers led by Dr. Potkonjak from the UCLA Department of Computer Science have developed a technique to detect hardware Trojans in integrated circuits.

High Thermal Conductivity Boron Arsenide For Thermal Management, Electronics, And Photonics Applications

UCLA researchers in the Department of Mechanical & Aerospace Engineering have developed a novel boron arsenide (BAs) material that has an ultra-high thermal conductivity of 1300 W/mK and low cost of synthesis and processing.

Energy Radiator Using Strain-Mediated Spin Torque Nano-Oscillator (S-STNO)

UCLA researchers in the Department of Mechanical and Aerospace Engineering have developed an energy radiator based on a spin torque nano-oscillator that does not require the application of an external field.

Magnetoelectric Device with Two Dielectric Barriers

UCLA researchers in the Department of Electrical and Computer Engineering have developed a magnetoelectric memory device that uses two dielectric barriers for improved voltage-controlled magnetic anisotropy (VCMA) and tunnel magnetoresistance (TMR) properties.

Electrical Charge Balancing Scheme For Functional Stimulation Using Pulse Width Compensation

UCLA researchers in the Department of Bioengineering have developed a novel electrical charge cancellation scheme to effectively remove residual charge on an electrode, achieving greater precision for lesser hardware cost, while maintaining a surgically implantable small size without extra pulse insertion.

An Improved On-Chip Crosstalk Noise Model

Researchers led by Jason Cong from the Department of Computer Science at UCLA have developed an improved on-chip crosstalk noise model to optimize integrated circuit design.

Deep Learning Artificial Intelligence System for Accurate Patent Prior Art Search

Researchers at the University of California, Davis have developed an artificial intelligence system that utilizes a deep learning neural network and an autoencoder to identify prior patent applications relevant to any proposed or filed new patent application.

Ultra-Low-Power Reference Clock Generation

UCLA researchers in the Department of Electrical and Computer Engineering have developed a novel ultra-low power crystal oscillator architecture that achieves the lowest reported power consumption.

Methods And Systems For Magnetoelectronic Elements And Arrays

UCLA researchers in the Department of Electrical Engineering have developed a magnetoelectric memory array, which uses a crossbar architecture to achieve high density.

A Nonvolatile Magnetoelectric Random Access Memory Circuit

UCLA researchers in the Department of Electrical Engineering have developed a nonvolatile random-access memory circuit (MeRAM) that is very dense, fast, and consumes extremely low power.

A Read-Disturbance-Free Nonvolatile Content Adressable Memory

UCLA researchers in the Department of Electrical Engineering have developed read-disturbance-free content addressable memory (CAM) using voltage controlled magneto-electric tunnel junctions (MEJs).

Voltage-Controlled Magnetic Memory Element With Canted Magnetization

UCLA researchers in the Department of Electrical Engineering have developed a method for voltage-controlled switching of the magnetization direction in MeRAM circuits.

Magnetoresistance Sensor With Perpendicular Anisotropy

UCLA researchers in the Department of Electrical Engineering have invented a novel magnetic sensor design that is highly sensitive and linear, with tunable response and low power consumption.

Voltage-Controlled Magnetic Tunnel Junction Switch

UCLA researchers in the Department of Electrical Engineering have developed a voltage-controlled magnetic tunnel junction switch that can switch the magnetization of a magnetic bit (i.e., in a free layer) from one state to another using an applied voltage.

Body Voltage Sensing Based Short Pulse Reading Circuit For STT-RAM

UCLA researchers in the Department of Electrical & Computer Engineering have invented a novel circuit design that performs high speed and reliable data reading operations for resistive device-based memory applications.

Broadband Comb-Based Spectrum Sensing

Researchers at the UCLA Department of Electrical & Computer Engineering have developed a millimeter-wave spectrum analyzer that uses a non-linear fast switch to generate a broadband frequency comb local oscillator (LO) with a tunable repetition rate.

  • Go to Page: