Articles tagged with Neural Net Processing
NeuroMechFly v2 simulates how a fruit fly navigates through its environment while reacting to sights, smells, and obstacles. The model can track moving objects visually or navigate towards an odor source, while avoiding obstacles in its path, enabling researchers to study brain-body coordination and animal intelligence.
Yihao Zheng and his team are developing a fiber-optic probe that analyzes artery blockages in the brain and guides procedures for blockage removal. The technology uses light and advanced calculations to determine the properties of blood clots, enabling doctors to make informed decisions about how to remove them.
A deep-learning algorithm developed by astronomer David Harvey can untangle the complex signals of self-interacting dark matter and AGN feedback in galaxy cluster images. The Inception model achieved an accuracy of 80% under ideal conditions, showcasing its potential for analyzing vast amounts of space data.
Researchers at EPFL developed a next-generation miniaturized brain-machine interface capable of direct brain-to-text communication on tiny silicon chips. The MiBMI system can decode neural signals generated when a person imagines writing letters or words with high accuracy and low power consumption.
UCF's STRONG-AI initiative aims to uplift bright, low-income undergraduate students in pursuing well-rounded AI education through faculty and peer mentorship and scholarship. The program has received over 150 applications and will select 10-15 students annually based on financial aid eligibility and academic success.
A new AI model developed by researchers at the University of British Columbia can accurately predict if a patient receiving cancer care will require mental health services. The AI analyzes oncologist's notes and identifies subtle clues that suggest a patient may benefit from early psychiatric or counselling interventions.
Researchers found that neural networks use a similar path to chart their way from ignorance to truth when presented with images, despite varying network designs and training recipes. This commonality holds the potential for developing more efficient image classification algorithms, reducing the computational power required by AI systems.
A new study highlights the importance of differentiating between formal and functional competence in language learning models. Researchers argue that leveraging human neuroscience insights can help develop more powerful AIs that mimic the brain's modularity, leading to improved performance and natural user interaction.
A new depth from focus/defocus approach, DDFS, combines model-based and learning-based strategies to achieve notable improvements in performance and applicability. The proposed method outperformed state-of-the-art methods in various metrics for several image datasets.
A researcher has developed a chatbot with expertise in nanomaterials, leveraging document-retrieval method to provide accurate context. The bot uses embedding to categorize and link information quickly, generating factual responses sourced from trusted documents.
The European Union's AI act could enable AI to access our subconscious minds, potentially leading to manipulation. According to Ignasi Beltran de Heredia, only 5% of brain activity is conscious, and the remaining 95% operates subconsciously, making it difficult for us to control or even be aware of.
A Lancaster University academic argues that AI and algorithms contribute to polarization, radicalism, and political violence, posing a threat to national security. The paper examines how AI has been securitized throughout its history, highlighting the need for better understanding and management of its risks.
Researchers are combining biology, physics, computer science, and engineering to design electric circuits that mimic the brain's adaptive behavior. The goal is to create a more efficient AI application that can learn from history and adapt without significant energy consumption.
Developing a technique to create conductive polymer wire connections between electrodes enables artificial neural networks that overcome the limits of traditional computer hardware. The approach allows researchers to control and train the network using small voltage pulses.
Engineers at Rice University and the University of Maryland developed NeuWS, a technology that can undo light scattering effects, enabling full-motion video through various media. The technology measures wavefronts to rapidly decipher phase information, overcoming the 'holy grail problem' in optical imaging.
Scientists measured brain waves in participants and artificial intelligence systems to reveal similarities in how the brain interprets speech. The study provides a window into the operation of AI systems, which have been advancing rapidly but remain largely opaque.
Researchers at the University of Pennsylvania School of Engineering and Applied Science have created a photonic device that provides programmable on-chip information processing without lithography. This breakthrough enables superior accuracy and flexibility for AI applications, overcoming limitations of traditional electronic systems.
A new neural network, CD-GAN, uses common sense knowledge to enhance text descriptions and generate images of birds at three resolution levels. The system achieved competitive scores against other image generation methods, producing vivid and natural-looking images.
A new study uses Fourier analysis to understand how deep neural networks learn complex physics. By analyzing the equation of a fully trained model, researchers were able to identify crucial information about how the network learns and generalizes. This breakthrough could accelerate the use of scientific deep learning in climate science.
Researchers created synthetic knee x-ray images to complement real images in osteoarthritis classification. Medical experts were unable to distinguish between authentic and synthetic images, highlighting the potential of synthetic data for collaboration and testing.
Researchers have developed a deep learning algorithm that can accurately assess the stage of head and neck cancer using standard CT scans, outperforming expert radiologists. The algorithm demonstrated superior accuracy in measuring the extent of cancer spread, especially for patients with high-risk disease.
Omnipose, a deep learning software, can identify various types of tiny objects in micrographs with high precision, including bacteria of all shapes and sizes. It overcomes limitations of previous approaches by handling object overlap and detecting cell intoxication, making it a game-changer for biological image analysis.
The new computer chip uses a transistor-free design that eliminates data transfer time and minimizes energy consumption. It offers up to 100 times faster performance than conventional computing architectures, making it ideal for AI applications.
Researchers at Emory University used machine learning and fMRI to analyze a dog's brain activity while watching videos. The results show that dogs are more attuned to actions in their environment than to who or what is performing the action. This study offers proof of concept for decoding canine visual perception.
Researchers developed a flexible, stretchable computing chip that processes information like a human brain to analyze health data. The device aims to change the way health data is processed, enabling continuous tracking of health without sending data wirelessly.
A team of researchers at Osaka University has created a machine learning system that can virtually remove buildings from a live view, streaming in real-time on a mobile device. This technology can help accelerate the process of urban renewal based on community agreement, reducing conflicts and delays.
A new AI-powered mental health application, FuturSelf, uses machine learning to identify the shortest path to mental stability. The system offers personalized recommendations for improving long-term well-being.
Researchers designed a modular AI chip that can be easily upgraded by swapping out layers, reducing the need for new devices. The chip uses optical communication to transmit information between layers, enabling high versatility in edge computing applications.
MIT researchers develop ExSum, a framework to formalize explanations of machine-learning models into quantifiable rules. This allows for testing assumptions about model behavior and reveals unexpected insights, such as negative words having sharper contributions to model decisions.
Artificial Intelligence can now identify legendary batting techniques used by Sir Donald Bradman and modern players. Researchers developed a deep learning computer vision AI model to detect lateral backlift batters from straight ones.
A study found that trainee teachers who received AI-generated feedback improved their diagnostic reasoning, identifying potential learning difficulties in pupils more accurately. The AI system analyzed the trainees' work and provided clear, adaptive feedback.
Researchers have developed a new method called Shared Interest that enables users to aggregate, sort, and rank individual explanations of a machine-learning model's reasoning. This technique uses quantifiable metrics to compare how well the model's reasoning matches human thinking, helping to uncover concerning trends in decision-making.
Researchers at MIT developed a framework for robotic manipulation systems that can perform complex tasks using a two-stage learning process. This allows robots to learn abstract ideas about manipulating deformable objects, such as pizza dough, and execute skills to complete tasks.
Researchers developed MonoCon, a new AI technique that enables accurate identification of 3D objects in 2D images. By incorporating auxiliary context, the method improves object detection and estimation accuracy, paving the way for safer and more robust autonomous vehicles.
A new study explores the problem of shortcuts in a popular machine learning method and proposes a solution that can prevent shortcuts by forcing the model to use more data. By removing simpler characteristics and asking the model to solve the task two ways, researchers reduce the tendency for shortcut solutions and boost performance.
A new algorithm, Phe2vec, accurately identified patients with certain diseases, outperforming traditional methods in classifying diagnoses. The study suggests that this automation will facilitate further research in clinical informatics.
Researchers at Technical University of Munich have developed a new machine learning algorithm that can analyze complex markets and their equilibrium strategies. This breakthrough has potential applications in auction theory, wireless spectrum auctions, and more.
The team used machine learning technique generative adversarial networks to digitally remove clouds from aerial images, generating accurate datasets of building image masks. This work may help automate computer vision jobs critical to civil engineering, enabling the detection of buildings in areas without labeled training data.