Innovations in Brain-Computer Interfaces

UC Berkeley and UCSF just brought real-time speech back to someone who couldn’t speak for 18 years (insane!). For people with paralysis and anarthria, the delay and effort of current AAC tools can make natural conversation nearly impossible. 𝗧𝗵𝗶𝘀 𝗻𝗲𝘄 𝗔𝗜-𝗱𝗿𝗶𝘃𝗲𝗻 𝗻𝗲𝘂𝗿𝗼𝗽𝗿𝗼𝘀𝘁𝗵𝗲𝘀𝗶𝘀 𝘀𝘁𝗿𝗲𝗮𝗺𝘀 𝗳𝗹𝘂𝗲𝗻𝘁, 𝗽𝗲𝗿𝘀𝗼𝗻𝗮𝗹𝗶𝘇𝗲𝗱 𝘀𝗽𝗲𝗲𝗰𝗵 𝗱𝗶𝗿𝗲𝗰𝘁𝗹𝘆 𝗳𝗿𝗼𝗺 𝗯𝗿𝗮𝗶𝗻 𝘀𝗶𝗴𝗻𝗮𝗹𝘀 𝗶𝗻 𝗿𝗲𝗮𝗹 𝘁𝗶𝗺𝗲 𝘄𝗶𝘁𝗵 𝗻𝗼 𝘃𝗼𝗰𝗮𝗹𝗶𝘇𝗮𝘁𝗶𝗼𝗻 𝗿𝗲𝗾𝘂𝗶𝗿𝗲𝗱. 1. Restored speech in a participant using 253-channel ECoG, 18 years after brainstem stroke and complete speech loss. 2. Trained deep learning decoders to synthesize audio and text every 80 ms based on silent speech attempts, with no vocal sound needed. 3. Streamed speech at 47.5 words per minute with just 1.12s latency = 8× faster than prior state-of-the-art neuroprostheses. 4. Matched the participant’s original voice using a pre-injury recording, bringing back not just words but vocal identity. Bimodal decoder architecture they used was cool. It's interesting how they got to low-latency and a synchronized output from the system. This was done by sharing a neural encoder and employing separate joiners and language models for both acoustic-speech units and text Other tidbits used was convolutional layers with unidirectional GRUs and LSTM-based language models. Absolutely love seeing AI used in practical ways to bring back joy and hope to people who are paralyzed!! Here's the awesome work: https://lnkd.in/ghqX5EB2 Congrats to Kaylo Littlejohn, Cheol Jun Cho, Jessie Liu, Edward Chang, Gopala Krishna Anumanchipalli, and co! I post my takes on the latest developments in health AI – 𝗰𝗼𝗻𝗻𝗲𝗰𝘁 𝘄𝗶𝘁𝗵 𝗺𝗲 𝘁𝗼 𝘀𝘁𝗮𝘆 𝘂𝗽𝗱𝗮𝘁𝗲𝗱! Also, check out my health AI blog here: https://lnkd.in/g3nrQFxW

AI just gave a paralyzed woman her voice back. In 2016, Ann, a 30-year-old teacher, suffered a stroke that left her unable to speak or move - trapped in her own body with Locked-In Syndrome for almost two decades. But now, thanks to a breakthrough brain-computer interface (BCI), she is communicating again - through a digital avatar. This new AI-powered technology decodes brain signals directly into speech and facial expressions. Here’s how the team at University of California, San Francisco made this breakthrough: 1. Brain signal decoding Researchers implanted 253 microelectrodes on the surface of Ann’s brain, capturing the brain signals that would normally control speech. This allowed her to communicate at 80 words per minute, just by thinking about them. 2. Recreating a natural voice Researchers used a sophisticated AI that synthesized Ann’s voice from a pre-stroke recording - her wedding day speech. This restoration wasn’t just robotic speech generation, it brought back her real voice. 3. Bringing emotion and expression back The team went further by combining speech synthesis with facial animation. A screen displayed Ann’s digital avatar, translating her brain signals into facial expressions, allowing it to smile, frown, and express emotions along with her restored voice. 4. The road to independence The next step in this research was to develop a wireless version of the system that would free Ann (and others like her) from the need for physical connections to a computer. This is life-changing tech that opens new doors for millions of people living with severe paralysis. It is a pivotal moment in the intersection of AI, neuroscience, and healthcare. But there's one concern: accessibility. While this technology is revolutionary, its high costs make it inaccessible for many who need it most. Could AI-powered speech technology be the future of healthcare for those with paralysis? Video credit: UC San Francisco (UCFS) on YouTube. #innovation #ai #technology #healthcare

Researchers have successfully used a brain implant coupled with AI to enable a bilingual individual, unable to articulate words due to a stroke, to communicate in both English and Spanish. This development not only enhances our understanding of how the brain processes language but also opens up new possibilities for restoring speech to those unable to communicate verbally. Known as Pancho, the participant demonstrated the ability to form coherent sentences in both languages with impressive accuracy, thanks to the neural patterns recognized and translated by the AI system. The findings suggest that different languages may not occupy distinct areas of the brain as previously thought, hinting at a more integrated neural basis for multilingualism. This technology represents a significant leap forward in neuroprosthetics, offering hope for personalized communication restoration in multilingual individuals. Key Insights: Dual Language Decoding 🗣️ - The AI system can interpret and translate neural patterns into both Spanish and English, adjusting in real-time. High Accuracy 🎯 - Achieved an 88% accuracy in distinguishing between languages and 75% in decoding full sentences. Unified Brain Activity 🧠 - Challenges prior assumptions with findings that both languages activate similar brain areas. Future Applications 🔍 - Potential expansion to other languages with varying linguistic structures, enhancing universal applicability. Enhanced Connection 💬 - Focuses not just on word replacement but on restoring deep personal connections through communication. https://buff.ly/3V8SiXe?

The FDA just greenlit more brain implant trials. The number of patients with brain chip implants is set to double in a year. Elon's Neuralink has been leading the charge, but now, Apple wants in. These 4 companies are redefining human evolution: Fewer than 100 people worldwide have permanent brain-computer interfaces. These aren't sci-fi fantasies but medical devices helping paralyzed patients communicate and control technology. Morgan Stanley projects a $1B annual market by 2041, reflecting the massive medical potential. These implants create direct neural pathways to restore functions, potentially transforming treatment for paralysis, blindness, depression, and Alzheimer's. 1. SYNCHRON: Least invasive approach • Electrode mesh runs through the brain's blood vessels • No skull opening required • Partnered with Apple for Vision Pro integration • Patient control with eye tracking and "thought clicks" 2. PRECISION NEUROSCIENCE: Surface approach • 1,024 electrodes on brain surface through tiny skull slit • Wireless system with nothing through skin • Goal: Translating thought directly to speech • Human testing next year 3. PARADROMICS: Data-focused approach • Coin-like implant with 421 electrodes extending 1.5mm into the brain • Ultra-fast connection compared to competitors • Electrodes so tiny brain might not notice them • Human trials start this year in the FDA breakthrough program 4. NEURALINK: Deep-brain approach • Electrodes penetrate 7mm via a specialized robot • Wireless system for thought control of devices • One patient is already designing 3D models and playing games with thought Each approach balances a fundamental tradeoff: Deeper penetration = more precise control, but higher risks Surface placement = safer but less detailed neural information Brain-computer interfaces could one day become as common as cochlear implants. The question isn't if this technology will transform humanity, but when. - Thanks for reading! I'm Baptiste Parravicini: • Tech entrepreneur & API visionary • Co-founder of APIdays, the world's leading API conference • Passionate about AI integration & tech for the greater good Want more on becoming the future of tech? Check out the comments ⬇️

Breaking Accessibility Barriers: Synchron’s BCI + Apple Vision Pro Synchron has reached a groundbreaking milestone by integrating its brain-computer interface (BCI) with Apple’s Vision Pro headset, enabling users to control the device using only their thoughts. This revolutionary advancement was demonstrated by Mark, a 64-year-old ALS patient, who effortlessly played Solitaire, watched Apple TV, and sent text messages without any physical movement. Key Highlights: • Innovative Technology: Synchron’s Stentrode BCI is implanted via a minimally invasive procedure through the jugular vein, avoiding open brain surgery. It detects motor intent signals from the brain and wirelessly transmits them to control digital devices. • Real-World Impact: Mark, who has lost the use of his hands, has been using the BCI twice a week since August 2023. He likens this new method of control to using his iPhone, iPad, and computer, thanks to seamless integration with Apple’s ecosystem. • Future Prospects: Synchron has implanted its BCI in ten patients across the U.S. and Australia and is gearing up for larger clinical trials. The company is also seeking FDA approval for broader commercialization. • Broader Implications: This technology holds promise for enhancing accessibility in various fields, including healthcare and rehabilitation, and could revolutionize how individuals with severe physical disabilities interact with digital environments. This collaboration between Synchron and Apple is a beacon of progress, showcasing the potential of medical innovation to transform lives and make advanced technology accessible to everyone. 🌟 #Accessibility #Innovation #BCI #AppleVisionPro #Neurotechnology #HealthcareInnovation #FutureTech #DRGPT

Yesterday, we explored how multimodal AI could enhance your perception of the world. Today, we go deeper into your mind. Let's explore the concept of the Cranial Edge AI Node ("CortexPod"). We’re moving from thought to action, like a cognitive copilot at the edge. Much of this is already possible: neuromorphic chips, lightweight brain-sensing wearables, and on-device AI that adapts in real time. The CortexPod is a conceptual leap; a cranial-edge AI node that acts as a cognitive coprocessor. It understands your mental state, adapts to your thinking, and supports you from the inside out. It's a small, discreet, body-worn device, mounted behind the ear or integrated into headgear or eyewear: ⭐ Edge AI Chipset: Neuromorphic hardware handles ultra-low-latency inference, attention tracking, and pattern recognition locally. ⭐ Multimodal Sensing: EEG, skin conductance, gaze tracking, micro-movements, and ambient audio. ⭐ On-Device LLM: A fine-tuned, lightweight language model lives locally. These are some example use cases: 👨⚕️ In Healthcare or Aviation: For high-stakes professions, it detects micro-signs of fatigue or overload, and flags risks before performance is affected. 📚 In Learning: It senses when you’re focused or drifting, and dynamically adapts the pace or style of content in real time. 💬 In Daily Life: It bookmarks thoughts when you’re interrupted. It reminds you of what matters when your mind starts to wander. It helps you refocus, not reactively, but intuitively. This is some recent research... 📚 Cortical Labs – CL1: Blending living neurons with silicon to create biological-silicon hybrid computers; efficient, adaptive, and brain-like. https://corticallabs.com/ 📚 BrainyEdge AI Framework: A lightweight, context-aware architecture for edge-based AI optimized for wearable cognitive interfaces. https://bit.ly/3EsKf1N These are some startups to watch: 🚀 Cortical Labs: Biological computers using neuron-silicon hybrids for dynamic AI. https://corticallabs.com/ 🚀 Cognixion: Brain-computer interfaces that integrate with speech and AR for neuroadaptive assistance. https://www.cognixion.com/ 🚀 Idun Technologies: Developing discreet, EEG-based neuro-sensing wearables that enable real-time brain monitoring for cognitive and emotional state detection. https://lnkd.in/gz7DNaDT 🚀 Synchron: A brain-computer interface designed to enable people to use their thoughts to control a digital device. https://synchron.com/ The timeline ahead of us: 3-5 years: Wearable CortexPods for personalized cognitive feedback and load monitoring. 8-10 years: Integrated “cognitive coprocessors” paired with on-device LLMs become common in work, learning, and well-being settings. This isn’t just a wearable; it’s a thinking companion. A CortexPod doesn’t just help you stay productive; it helps you stay aligned with your energy, thoughts, and intent. Next up: Subdermal Audio Transducer + Laryngeal Micro-Node (“Silent Voice”) 

In a groundbreaking livestream hosted on the social media platform X, Neuralink introduced its first human subject, Noland Arbaugh, a 29-year-old paralyzed man who, thanks to the company's pioneering brain implant, demonstrated his ability to control a computer cursor using only his thoughts. Having suffered paralysis from a diving accident eight years prior, Arbaugh's ability to play online chess and the video game Civilization marks a significant milestone in the development of brain-computer interfaces. Neuralink, co-founded by Elon Musk, aims to enable individuals with paralysis to interact with digital devices through thought alone, offering a new level of independence and interaction. Arbaugh's successful manipulation of a digital chess piece, as shared during the livestream, underscores the intuitive nature of the device's control mechanism, which he adapted to by imagining movements he would physically make. Beyond the technological marvel, this development represents a beacon of hope for many, promising to redefine the boundaries of human-machine interaction. As Neuralink continues to refine and test their device, it invites a broader conversation on the implications and potential of such technology. What are your thoughts on this technological advance? #technology #innovation #elonmusk

The Defense Advanced Research Projects Agency (DARPA)’s Next-Generation Nonsurgical Neurotechnology (N3) project is an ambitious initiative aiming to develop vast array of nanoscalar sensing and transmitting brain-computational interfaces (BCIs). An axiomatic attribute of such a system is obviating the burden and risks of neurosurgical implantation by instead introducing the nanomaterials via intranasally, intravenously and/or intraorally, and using electromagnetic fields to migrate the units to their distribution within the brain. It’s said that location is everything, and so too here. Arrays would require precise placement in order to engage specific nodes and networks, and it’s unknown if -and to what extent any “drift” might incur in system fidelity. The system works much like WiFi in that it’s all about parsing signal from the “noise floor” of the brain; but “can you hear me now?” takes on deeper implications when the sensing and transmitting dynamics involve “reading from” and “writing into” brain processes of cognition, emotions and behavior. I’d be the first one to argue for an “always faithful” paradigm of sensing and transmitting integrity; yet, even if the system and its workings are true to design, there’s still a possibility of components (and functions) being “hacked”. As work with Dr Diane DiEuliis has advocated, the need for “biocybersecurity-by-design” is paramount (not just for N3, but for all neurotech, given its essential reliance upon data). By intent, N3 holds promise in medicine; but the tech is also provocative for communications (of all sorts), and its dual-use is obvious. Yes, Pandora, this jar’s been opened. If we consider the sum-totaled operations of the embodied brain to be “mind”, and N3-type tech is aimed at remotely sensing and modulating these operations, then it doesn’t require much of a stretch to recognize that this is fundamentally “mind reading” and “mind control”, at least at a basic level. And that’s contentious. In full transparency, I served as a consulting ethicist on initial stages of N3, and the issues spawned by this project were evident, and deeply discussed. But discussion is not resolution, and the “goods” as well as the gremlins and goblins of N3 tech have been loosed into the real world. The real world is multinational, and DARPA – and the US – are not alone in pursuing these projects. Nations’ and peoples’ values, needs, desires, economics, allegiances, and ethics differ, and any genuine ethical discourses – and policy governances - must account for that. The need for a reality check is now; the question is whether there is enough rational capital in regulatory institutions’ accounts to cash the check without bouncing bankable benefits into the realms of burdens, risks and harms. #Neurotechnology #Nanotechnology #BCI #Ethics #Policy

From robotic to real? We are entering a new era of mind-controlled limbs. Neuroprosthetic limbs are no longer science fiction, they are rapidly transforming into natural extensions of the human body. A remarkable new review by Tian, Kemp and colleagues in Annals of Neurology lays out how brain and nerve interfaces are now converging to restore true limb function, especially when following a devastating injury, disease or amputation. Key Points: - The authors teach us that by combining brain-computer interfaces or BCIs w/ peripheral nerve signals, a generation of future prosthetics may be able to interpret intention and deliver real-time sensory feedback. - The advances are bringing us closer to natural limb function. - Advanced surgical techniques like targeted muscle reinnervation (TMR) and regenerative peripheral nerve interfaces (RPNIs) are facilitating nerves communicating w/ prosthetics through reinnervated muscle. - The overarching idea is to create a natural signal amplifier. - Users are beginning to feel texture, pressure and temperature. - Are we reawakening a sense of ownership over the limb? My take: There were 5 points that resonated w/ me about where prosthetic limbs are headed. 1- Today's prosthetic hands are smarter than ever. These hands can grab, hold and even feel objects w/ increasing precision. 2- We are learning to plug into the brain and it seems to be working. Thought controlled limbs are now entering real world trials. 3- Rewiring nerves into muscles offers more clear signals, improved speed, better accuracy and hopefully more natural movement. 4- One day a prosthetic limb may not just replace a lost one, but could it do the unthinkable and surpass it in function? 5- We are moving from clunky robots to more intuitive life like limbs. I think this story is not just about mobility, it’s about restoring human dignity. The future of neuroprosthetics will be more personal, intelligent and 'deeply human.' https://lnkd.in/d9XvqTBU Parkinson's Foundation Norman Fixel Institute for Neurological Diseases International Parkinson and Movement Disorder Society

Cortical Labs Unveils AI-Powered Biological Computer Using Human Brain Cells Australian startup Cortical Labs has introduced the CL1, a shoebox-sized biological computer that blends human brain cells with silicon chips to process information and run AI models. Marketed as the world’s first code-deployable biological computer, CL1 represents a radical shift in computing, leveraging living neurons to create a new kind of neural network. A Hybrid of Biology and Technology The CL1 system uses hundreds of thousands of cultivated neurons, roughly the size of an ant brain, which are kept alive in a nutrient-rich solution and integrated with silicon-based electronics. This combination allows users to deploy code directly onto living neurons, essentially teaching biological tissue to process and respond to data. According to Cortical Labs, the goal is to harness the adaptive and energy-efficient nature of human brain cells to tackle complex computational challenges. Advancing Biological Computing Cortical Labs first gained attention in 2022 when it taught human brain cells in a petri dish to play Pong. With CL1, the company has taken a fundamentally different approach, aiming to create a system where biological intelligence can be programmed like traditional software. The device includes circulatory pumps, gas mixing, and temperature control to sustain the neurons, effectively creating a “body in a box” that mimics a microenvironment for living tissue to function alongside hard silicon. Implications and Ethical Considerations Biological computing could revolutionize AI, robotics, and neuroscience, offering a potential alternative to traditional silicon-based computing that is more energy-efficient and adaptable. However, the integration of living brain cells in AI-driven technology raises ethical questions about the nature of consciousness, data privacy, and the treatment of biological components in computing. As biocomputing advances, CL1 represents a bold step toward merging artificial intelligence with human-like intelligence, potentially reshaping the future of machine learning and AI-driven problem-solving. Whether this technology can scale beyond research labs remains to be seen, but it marks a major milestone in the convergence of biology and computing.