Search Results - deep+physical+neural+network

4 Results

Sort By:

Securing Camera and Photography Systems From Deepfakes by Verifying Provenance and Reducing Attack Surfaces (Case No. 2024-270)

Summary: Researchers in the UCLA Department of Electrical and Computer Engineering have developed a multi-layer security framework to verify deepfake imagery data. Background: The exponential improvements in generative AI pose serious implication to the rise of synthetic media or “deepfakes”. Soon, deepfake images and videos will be...

Published: 9/27/2024 | Inventor(s): Alexander Vilesov, Achuta Kadambi, Yuan Tian, Nader Sehatbakhsh

Keywords(s): AI image security, Artificial Intelligence, artificial intelligence algorithms, Artificial Neural Network, Artificial Neural Network Artificial Neuron, artificial-intelligent materials, attack surface reduction, data security, Deep Learning, Deep learning-based sensing, deep physical neural network, deepfake, deepfake protection, deep-learning analysis algorithms, deep-learning fake (deepfake), generative artificial intelligence, image authenticity verification, image provenance, image signal processing, Medical artificial intelligence (AI), social media, third-party verification

Category(s): Software & Algorithms, Software & Algorithms > Artificial Intelligence & Machine Learning, Software & Algorithms > Image Processing, Software & Algorithms > Security & Privacy, Electrical, Electrical > Visual Computing, Electrical > Visual Computing > Video Processing

Method of Proficient Typing Using a Limited Number of Classes (Case No. 2024-063)

Summary: UCLA researchers in the Department of Electrical and Computer Engineering have developed a novel software algorithm to rapidly predict text using small keyboards for various applications, including mobile computing, gaming, and human-computer interactions. Background: Advancements in mobile computing have drastically changed everyday life...

Published: 11/6/2024 | Inventor(s): Jonathan Kao, Shreyas Kaasyap, John Zhou, Johannes Lee, Nima Hadidi

Keywords(s): Advanced Computing / AI, advanced computing methods, all-optical diffractive computing, Artificial Neural Network, Artificial Neural Network Artificial Neuron, assistive communication, background radiation, Bandwidth (Computing), Brain computer interface, brain machine interface, Classroom management software, Cloud Computing, composite scintillators, Database management/data entry, deep physical neural network, design software, edge computing, fast scintillators, gamma spectroscopy, graph neural network, HCI (Human Computer Interaction), high-Z organometallics, Human/Brain computer interfaces (BCI/HCI), human-centered computing, material characterization, Medical science computing, mobile computing, modular robotic system, nanocomposite scintillators, neural network, neural networks, neutrino detection, Optical computing, positron emission tomography (PET), predictive text, primary school software, radiation detection, recurrent neural networks, Robotics, robotics control, scintillators, second harmonic generation, secondary school software, self-sustaining computing, soft robotics, Software, Software & Algorithms, Software Development Tools, Software-enabled learning, Spatial computing, Stochastic Computing (SC), T6 keyboard, T9 keyboard, visual computing, wafer-scale computing

Category(s): Software & Algorithms, Software & Algorithms > Artificial Intelligence & Machine Learning, Software & Algorithms > Communication & Networking

The Growing Role of Digital Pathology and Machine Learning in Cancer Diagnostics (UCLA Case No. 2021-134)

Summary: Researchers at UCLA's Department of Radiological Sciences have developed an active learning methodology for digital pathology image analysis, addressing challenges posed by inconsistent annotations and revolutionizing the training of diagnostic algorithms. Background: The global digital pathology market is anticipated to experience significant...

Published: 8/9/2023 | Inventor(s): Corey Arnold, Wenyuan Li, Jiayun Li, William Speier

Keywords(s): active learning, Artifical Intelligence (Machine Learning, Data Mining), Artificial Intelligence, Artificial Neural Network, artificial-intelligent materials, computational imaging task, convolutional networks, curriculum learning, Deep Learning, deep physical neural network, Digital Pathology, dynamic identification, Histopathological image analysis, histopathology images, Image Processing, Magnetic Resonance Imaging Pathology, Medical Devices and Materials, Medical Imaging, noisy annotations, noisy label detection, pathology image analysis

Category(s): Software & Algorithms, Software & Algorithms > Image Processing, Electrical > Imaging, Medical Devices > Medical Imaging

Mechanical Neural-Network-Based Metamaterial That Learns Its Properties (Case No. 2022-317)

Summary: UCLA researchers in the Department of Mechanical and Aerospace Engineering have developed a new type of meta-material that can actively adapt its mechanical properties from exposure to external stimuli. Background: As technologies have evolved, humans developed new methods to produce unique materials, such as plastics, steels and composites,...

Published: 10/29/2024 | Inventor(s): Jonathan Hopkins, Erwin Mulder, Ryan Hansen Lee

Keywords(s): active actuators, additive manufacturing, Artificial Neural Network, artificial-intelligent materials, Composite Material, Composite Materials, Construction Materials, deep physical neural network, Flexible Electronics, Functional Materials, lattice structures, Materials, Medical Devices and Materials, meta materials, microarchitectured materials, Nanomaterials, Smart Material, stiffness tunability

Category(s): Materials, Mechanical, Electrical, Electrical > Signal Processing, Software & Algorithms