Lifeboat Foundation: Safeguarding Humanity
Toggle light / dark theme

Blog

Category: robotics/AI – Page 138

Neural responses in early, but not late, visual cortex are well predicted by random-weight CNNs with sufficient model complexity

Convolutional neural networks (CNNs) were inspired by the organization of the primate visual system, and in turn have become effective models of the visual cortex, allowing for accurate predictions of neural stimulus responses. While training CNNs on brain-relevant object-recognition tasks may be an important pre-requisite to predict brain activity, the CNN’s brain-like architecture alone may already allow for accurate prediction of neural activity. Here, we evaluated the performance of both task-optimized and brain-optimized convolutional neural networks (CNNs) in predicting neural responses across visual cortex, and performed systematic architectural manipulations and comparisons between trained and untrained feature extractors to reveal key structural components influencing model performance. For human and monkey area V1, random-weight CNNs employing the ReLU activation function, combined with either average or max pooling, significantly outperformed other activation functions. Random-weight CNNs matched their trained counterparts in predicting V1 responses. The extent to which V1 responses can be predicted correlated strongly with the neural network’s complexity, which reflects the non-linearity of neural activation functions and pooling operations. However, this correlation between encoding performance and complexity was significantly weaker for higher visual areas that are classically associated with object recognition, such as monkey IT. To test whether this difference between visual areas reflects functional differences, we trained neural network models on both texture discrimination and object recognition tasks. Consistent with our hypothesis, model complexity correlated more strongly with performance on texture discrimination than object recognition. Our findings indicate that random-weight CNNs with sufficient model complexity allow for comparable prediction of V1 activity as trained CNNs, while higher visual areas require precise weight configurations acquired through training via gradient descent.

The authors have declared no competing interest.

Neural networks and Raman spectroscopy identify microplastic invaders for a cleaner world

A research team led by Prof. Gao Xiaoming from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences has improved residual neural networks to accurately classify and identify microplastics using low-quality Raman spectra, even under non-ideal experimental conditions.

“It detects and classifies microplastics when the data is cluttered with noise,” said Prof. Gao, “and it does this without overloading computing power.”

The research results are published in Talanta.

Understanding the origin of magnetic moment enhancement in novel alloys

Magnetic materials have become indispensable to various technologies that support our modern society, such as data storage devices, electric motors, and magnetic sensors.

High-magnetization ferromagnets are especially important for the development of next-generation spintronics, sensors, and high-density data storage technologies. Among these materials, the iron-cobalt (Fe-Co) alloy is widely used due to its strong magnetic properties. However, there is a limit to how much their performance can be improved, necessitating a new approach.

Some earlier studies have shown that epitaxially grown films made up of Fe-Co alloys doped with heavier elements exhibit remarkably high magnetization. Moreover, recent advances in computational techniques, such as the integration of machine learning with ab initio calculations, have significantly accelerated the search for new material compositions.

Genetically supported targets and drug repurposing for brain aging: A systematic study in the UK Biobank

Moreover, among the 37 druggable genes supported by at least two pieces of genetic evidence, we have identified 28 drugs targeting MPL, CA4, TUBB, and RRM1, although neither in clinical trials nor reported previously have the potential to be repurposed for slowing down brain aging. Specifically, four drugs, namely, avatrombopag, eltrombopag, lusutrombopag, and romiplostim, which are typically used for thrombocytopenia, act as agonists for MPL. As mentioned above, MPL is a thrombopoietin receptor and has been linked to platelet count and brain morphology in the GWAS catalog. Notably, platelet signaling and aggregation pathway is enriched using the 64 MR genes. It is worth noting that platelet count decreases during aging and is lower in men compared to women (84). A recent study of platelets has also revealed that platelets rejuvenate the aging brain (85). Schroer et al. (86) found that circulating platelet-derived factors could potentially serve as therapeutic targets to attenuate neuroinflammation and improve cognition in aging mice (86). Park et al. (87) reported that longevity factor klotho induces multiple platelet factors in plasma, enhancing cognition in the young brain and decreasing cognitive deficits in the aging brain (87). Leiter et al. (88) found that platelet-derived platelet factor 4, highly abundant chemokine in platelets, ameliorates hippocampal neurogenesis, and restores cognitive function in aged mice. These findings suggest that the aforementioned drugs may enhance the expression of MPL, leading to increased platelet count and potentially contributing to a delay in brain aging. It is important to note that determining the significant tissue(s) for gene prioritization can be challenging. Although brain tissues may be more biologically relevant for brain aging, circulating proteins have the capability to modulate brain aging as well (89, 90). Six drugs (cladribine, clofarabine, gallium nitrate, gemcitabine, hydroxyurea, and tezacitabine) are inhibitors of RRM1, whereas 12 drugs (brentuximab vedotin, cabazitaxel, crolibulin, indibulin, ixabepilone, paclitaxel, plinabulin, podofilox, trastuzumab emtansine, vinblastine, vinflunine, and vinorelbine) are inhibitors of TUBB. Most of these drugs targeting RRM1 and TUBB are antineoplastic agents used in cancer treatment. In addition, six drugs (acetazolamide, brinzolamide, chlorothiazide, methazolamide, topiramate, and trichlormethiazide) are inhibitors of CA4 and most of them are used for hypertension.

There are a few limitations to this study: (i) The accurate estimation of brain age is hindered by the lack of ground-truth brain biological age and discrepancies between brain biological age and chronological age in supposedly healthy individuals. The estimated brain age derived from MRI data includes inherent biases (91). Although our model has shown better generalization performance compared to other models, there is always an expectation for a more accurate brain age estimation model that can deliver more robust outcomes for clinical applicants (3, 91). (ii) Potential data bias may affect the findings of this comprehensive study. For instance, the brain age estimation model and GWAS summary statistics primarily relied on cohorts of European white individuals, potentially overlooking druggable targets that would be effective in individuals of non-European ancestry. Validation using genomic and clinical data from more diverse populations could help remedy this limitation. (iii) Validation on independent discovery and replication cohorts would enhance the reliability of the identified genes as drug targets for the prevention of brain aging. Although we maximized statistical power using the UKB data as a large discovery cohort, the absence of a discovery-replication design is unavoidable. As large-scale datasets containing both MRI and genome-wide genotypes were not widely available, we used a combination of GWAS for BAG, MR with xQTL, colocalization analysis, MR-PheWAS, and the existing literature to carefully identify genetic targets that are supported by evidence for their involvement in brain aging. With the availability of more comprehensive proteomics platforms and the inclusion of more diverse non-European ancestry populations in studies, it is likely to replicate and validate our results. (iv) Brain aging is a complex process involving numerous potential causes, such as aging of cerebral blood vessels (92), atrophy of the cerebral cortex (93), etc. These causes may overlap and interweave, undergoing considerable changes during brain aging (48). Although our study demonstrates the utility of systematically analyzing GWAS alongside extensive brain imaging information and xQTL analysis to enrich the identification of drug targets, there remains a need for machine learning or statistical methods to address the various risk factors associated with brain aging. Fine-grained analysis is a must to comprehend the individualized causes and trajectories of brain aging, enabling the identification of effective drug targets and the use of precision medications for the purpose of slowing down or even preventing brain aging. There is also an increasing need for comprehensive studies spanning different tissues and organs to evaluate tissue-or organ-specific effects of targets, enabling the systematic prevention or treatment of human aging. (v) This study did not explore adverse effects of the rediscovered antiaging drugs. This is particularly important because healthy aging individuals should be encouraged to consider the potential risks associated with taking medications or supplements for slowing down aging as these interventions may have unintended negative consequences for both individuals and society. Alternatively, it is worthwhile to explore nonpharmacological interventions/digital therapies that can help preserve mental and physical fitness in people during aging.

In summary, we present a systematic study for identify genetically supported targets and drugs for brain aging with deep learning-based brain age estimation, GWAS for BAG, analysis of the relation between BAG and brain disorders, prioritization of targets using MR and colorization analysis for BAG with xQTL data, drug repurposing for these targets of BAG, and PheWAS. Our results offer the potential to mitigate the risk associated with drug discovery by identifying genetically supported targets and repurposing approved drugs to attenuate brain aging. We anticipate that our findings will serve as a valuable resource for prioritizing drug development efforts for BAG, shedding light on the understanding of human brain aging and potentially extending the health span in humans.

Apple M4 Max chip

Learn how to build or just use Alex Ziskind’s LLM Hardware Calculator.

Understand what hardware you need for the model you want to run locally.

This M4 Max 16 MacBook Pro can handle some of the larger language models.

https://amzn.to/4kyog9V

Apple 2024 MacBook Pro Laptop with M4 Max, 14‑core CPU, 32‑core GPU: Built for Apple Intelligence, 16.2-inch Display, 36GB Unified Memory, 1TB SSD Storage; Silver with AppleCare+ (3 Years)https://m.media-amazon.com/images/I/51MOSiURIHL._AC_SX425_.jpg’:[425,425],’https://m.media-amazon.com/images/I/51MOSiURIHL._AC_SX522_.jpg’:[522,522],’https://m.media-amazon.com/images/I/51MOSiURIHL._AC_SX569_.jpg’:[569,569],’https://m.media-amazon.com/images/I/51MOSiURIHL._AC_SX385_.jpg’:[385,385],’https://m.media-amazon.com/images/I/51MOSiURIHL._AC_SX679_.jpg’:[679,679],’https://m.media-amazon.com/images/I/51MOSiURIHL._AC_SX466_.jpg’:[466,466],’https://m.media-amazon.com/images/I/51MOSiURIHL._AC_SX342_.jpg’:[342,342]}/

Continue reading “Apple M4 Max chip” | >

Researchers create gel that can self-heal like human skin

We all encounter gels in daily life – from the soft, sticky substances you put in your hair, to the jelly-like components in various foodstuffs. While human skin shares gel-like characteristics, it has unique qualities that are very hard to replicate. It combines high stiffness with flexibility, and it has remarkable self-healing capabilities, often healing completely within 24 hours after injury.

Until now, artificial gels have either managed to replicate this high stiffness or natural skin’s self-healing properties, but not both. Now, a team of researchers from Aalto University and the University of Bayreuth are the first to develop a hydrogel with a unique structure that overcomes earlier limitations, opening the door to applications such as drug delivery, wound healing, soft robotics sensors and artificial skin.

In the breakthrough study, the researchers added exceptionally large and ultra-thin specific clay nanosheets to hydrogels, which are typically soft and squishy. The result is a highly ordered structure with densely entangled polymers between nanosheets, not only improving the mechanical properties of the hydrogel but also allowing the material to self-heal.

Magnetic microrobots remove blood clots from sheep iliac artery

Researchers at the TechMed Center of the University of Twente and Radboud University Medical Center have removed blood clots with wireless magnetic robots. This innovation promises to transform treatment for life-threatening vascular conditions like thrombosis.

Cardiovascular diseases such as thrombosis are a major global health challenge. Each year worldwide, 1 in 4 people die from conditions caused by blood clots. A blood clot blocks a blood vessel, preventing the blood from delivering oxygen to certain areas of the body.

Minimally invasive Traditional treatments struggle with clots in hard-to-reach areas. But magnetic microrobots bring hope to patients with otherwise inoperable clots. The screw-shaped robots can navigate through intricate vascular networks since they are operated wirelessly.

Scientists develop high-performance permanent magnet without expensive heavy rare earth elements

The Nano Materials Research Division at the Korea Institute of Materials Science (KIMS), led by Dr. Tae-Hoon Kim and Dr. Jung-Goo Lee has successfully developed a grain boundary diffusion process that enables the fabrication of high-performance permanent magnets without the use of expensive heavy rare earth elements. This pioneering technology marks the world’s first achievement in this field.

The findings are published in Acta Materialia.

Permanent magnets are key components in various high-value-added products, including electric vehicle (EV) motors and robots. However, conventional permanent magnet manufacturing processes have been heavily dependent on heavy rare earth elements, which are exclusively produced by China, leading to high resource dependency and .

“Incipient Ferroelectricity” Turns Field-Effect Transistors into Efficient Neuron-Like Devices

“‘Incipient ferroelectricity’ means there’s no stable ferroelectric order at room temperature,” lead author Dipanjan Sen explains of the property that the team investigated. “Instead, there are small, scattered clusters of polar domains. It’s a more flexible structure compared to traditional ferroelectric materials.”

Typically, the “relaxor” behavior of incipient ferroelectric materials at room temperature is a drawback, making their operation less predictable and more fluid — but the team’s breakthrough was to approach it as an advantage instead, showing how it could be of use in devices like neuromorphic processors that increase machine learning and artificial intelligence performance by processing information like the neurons in the human brain.

“To test this,” co-author Mayukh Das says, “we performed a classification task using a grid of three-by-three pixel images fed into three artificial neurons. The devices were able to classify each image into different categories. This learning method could eventually be used for image identification and classification or pattern recognition. Importantly, it works at room temperature, reducing energy costs. These devices function similarly to the nervous system, acting like neurons and creating a low-cost, efficient computing system that uses a lot less energy.”

How to Train LLMs to “Think” (o1 & DeepSeek-R1)

In September 2024, OpenAI released its o1 model, trained on large-scale reinforcement learning, giving it “advanced reasoning” capabilities. Unfortunately, the details of how they pulled this off were never shared publicly. Today, however, DeepSeek (an AI research lab) has replicated this reasoning behavior and published the full technical details of their approach. In this article, I will discuss the key ideas behind this innovation and describe how they work under the hood.