cases / case_bci.html
Acedo's picture
Upload 21 files
dacdd5f verified
Raw History Blame Contribute Delete
21.6 kB
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1, viewport-fit=cover">
<meta name="claude:viewport-fit-sides" content="cover">
<title>CA3 · Brain implant</title>
<meta name="description" content="A brain-implant decoder learned seven new days with CA3 and kept the days it already decoded; every nightly update checked, kept or rolled back.">
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Source+Sans+3:wght@300;400;600;700&family=IBM+Plex+Mono:wght@400;500&display=swap">
<style>
:root{color-scheme:dark;--bg:#000;--bg2:#06080A;--panel:#0C1115;--line:rgba(255,255,255,.11);--line2:rgba(255,255,255,.06);
--ink:#F5F7F8;--ink2:#A4AFB5;--ink3:#7A868C;--blue:#7CC0E0;--red:#E8827C;--amber:#E9B36A;--green:#8FD6AE;
--f-ui:'Source Sans 3','Myriad Pro',Myriad,'Segoe UI',system-ui,-apple-system,Arial,sans-serif;
--f-mono:'IBM Plex Mono',ui-monospace,'SFMono-Regular',Menlo,Consolas,monospace;
--gl:max(20px,env(safe-area-inset-left,0px));--gr:max(20px,env(safe-area-inset-right,0px));
padding-top:env(safe-area-inset-top,0px);padding-bottom:env(safe-area-inset-bottom,0px)}
@media (min-width:980px){:root{--gl:max(40px,env(safe-area-inset-left,0px));--gr:max(40px,env(safe-area-inset-right,0px))}}
*{box-sizing:border-box}html{background:var(--bg);scroll-behavior:smooth}
body{margin:0;background:var(--bg);color:var(--ink);font-family:var(--f-ui);font-size:18px;line-height:1.5;font-variant-numeric:tabular-nums;-webkit-font-smoothing:antialiased}
a{color:var(--blue);text-decoration:none}a:focus-visible{outline:2px solid var(--blue);outline-offset:4px;border-radius:6px}
img,video{max-width:100%}h1,h2,h3{margin:0;text-wrap:balance}p{margin:0}[hidden]{display:none!important}
.wrap{max-width:1200px;margin:0 auto;padding-left:var(--gl);padding-right:var(--gr)}
header{position:sticky;top:0;z-index:20;background:rgba(0,0,0,.62);-webkit-backdrop-filter:blur(20px) saturate(180%);backdrop-filter:blur(20px) saturate(180%);border-bottom:1px solid var(--line2)}
header .wrap{display:flex;align-items:center;gap:22px;height:56px}
.brand{display:flex;align-items:center;gap:10px;font-weight:700;font-size:19px;letter-spacing:.08em;color:var(--ink)}.brand img{width:24px;height:24px}
.back{margin-left:auto;font-size:15px;color:var(--ink2)}.back:hover{color:var(--ink)}
.pill{font-size:14px;font-weight:600;color:#000;background:var(--ink);border-radius:999px;padding:7px 14px;white-space:nowrap}
.eyebrow{font-size:14px;letter-spacing:.22em;text-transform:uppercase;color:var(--blue);font-weight:600}
.hero{padding-block:clamp(56px,9vh,110px) 40px;background:radial-gradient(70% 60% at 50% 30%,#0F1C24 0%,#05090C 55%,#000 100%)}
.hero .head{display:flex;flex-direction:column;gap:20px;align-items:center;text-align:center}
.hero h1{font-size:clamp(38px,5.4vw,76px);line-height:1.03;font-weight:600;letter-spacing:-.03em;max-width:20ch}
.hero .sub{font-size:clamp(19px,1.8vw,23px);color:var(--ink2);max-width:46ch;line-height:1.42}
.hero .media{margin-top:44px;border-radius:20px;overflow:hidden;border:1px solid var(--line);background:#05080A}
.hero .media img,.hero .media video{display:block;width:100%;max-height:78vh;object-fit:contain}
.demo{display:inline-block;font-size:11px;letter-spacing:.14em;text-transform:uppercase;color:var(--ink3);border:1px solid var(--line);border-radius:6px;padding:3px 8px}
.specs{display:grid;grid-template-columns:repeat(4,minmax(0,1fr));margin-top:48px;border-top:1px solid var(--line)}
.specs div{padding:22px 18px 0 0;display:flex;flex-direction:column;gap:6px;min-width:0}
.specs .k{font-size:12px;letter-spacing:.2em;text-transform:uppercase;color:var(--ink3);font-weight:600}
.specs .v{font-size:clamp(28px,3vw,46px);font-weight:300;line-height:1.05;letter-spacing:-.03em;color:var(--blue)}
.specs .c{font-size:15px;color:var(--ink2)}
section.block{padding-block:clamp(70px,10vh,120px);border-top:1px solid var(--line2)}
section.block.alt{background:var(--bg2)}
.bh{display:flex;flex-direction:column;gap:14px;max-width:760px}
.bh .verb{font-size:13px;letter-spacing:.22em;text-transform:uppercase;font-weight:600;color:var(--blue)}
.bh .verb.r{color:var(--red)}.bh .verb.g{color:var(--ink3)}
.bh h2{font-size:clamp(30px,3.6vw,52px);font-weight:600;letter-spacing:-.025em;line-height:1.06}
.bh p{color:var(--ink2);font-size:clamp(18px,1.6vw,21px);line-height:1.45}
.pair{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));gap:8px;margin-top:40px}
.pair.three{grid-template-columns:repeat(3,minmax(0,1fr))}
.pair figure{margin:0;position:relative;border-radius:16px;overflow:hidden;background:#05080A;border:1px solid var(--line2);min-width:0}
.pair img,.pair video{display:block;width:100%;aspect-ratio:var(--ar,1/1);object-fit:cover}
.pair .px img{image-rendering:pixelated}
.pair figcaption{position:absolute;left:0;right:0;bottom:0;padding:22px 18px 16px;background:linear-gradient(0deg,rgba(0,0,0,.85),rgba(0,0,0,0));display:flex;flex-direction:column;gap:2px}
.pair .who{font-size:12px;letter-spacing:.18em;text-transform:uppercase;font-weight:600;color:var(--ink)}
.pair .num{font-size:clamp(34px,3.8vw,56px);font-weight:300;line-height:1;letter-spacing:-.035em}
.pair .bad .num{color:var(--red)}.pair .good .num{color:var(--blue)}.pair .neutral .num{color:var(--ink)}
.pair .what{font-size:14px;color:var(--ink2)}
.kp{display:flex;gap:40px;margin-top:30px;flex-wrap:wrap}
.kp b{display:block;font-size:clamp(36px,3.8vw,56px);font-weight:300;line-height:1;letter-spacing:-.035em;color:var(--blue);white-space:nowrap}
.kp b.r{color:var(--red)}.kp b.w{color:var(--ink)}
.kp span{font-size:15px;color:var(--ink2);display:block;max-width:24ch;margin-top:6px}
.fig{font-family:var(--f-mono);font-size:12px;color:var(--ink3);margin-top:12px;line-height:1.6}
.chips{display:flex;gap:8px;flex-wrap:wrap;margin-top:22px}
.chips span{font-family:var(--f-mono);font-size:12.5px;border:1px solid var(--line);border-radius:999px;padding:4px 10px;color:var(--ink2)}
.quote{margin-top:26px;font-family:var(--f-mono);font-size:clamp(15px,1.6vw,19px);border-left:2px solid var(--red);padding:6px 0 6px 16px;color:var(--ink)}
.quote small{display:block;color:var(--ink3);font-size:13px;margin-top:6px}
.quote.b{border-left-color:var(--blue)}.quote.g{border-left-color:var(--ink3)}
.charts{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));gap:14px;margin-top:40px}
.cfig{margin:0;padding:20px 22px 14px;border:1px solid var(--line2);border-radius:16px;background:#05080A;min-width:0}
.cfig figcaption{font-size:16px;color:var(--ink);margin-bottom:12px}.cfig figcaption span{color:var(--ink3);font-size:13px;margin-left:6px}
.cfig svg{display:block;width:100%;height:auto;overflow:visible}
.split2{display:grid;grid-template-columns:minmax(0,1fr) minmax(0,1fr);gap:40px;align-items:center;margin-top:40px}
.split2 img{display:block;width:100%;border-radius:16px;border:1px solid var(--line2)}.split2 .kp{margin-top:0;flex-direction:column;gap:26px}
.fp{margin-top:40px}.fp table{min-width:0}.fp td:nth-child(2){font-family:var(--f-mono);color:var(--blue)}
.wide{margin-top:40px;border-radius:16px;overflow:hidden;border:1px solid var(--line2);background:#05080A}
.wide img,.wide video{display:block;width:100%}
.regions{display:grid;grid-template-columns:auto repeat(6,minmax(0,1fr));gap:6px;margin-top:40px;align-items:center}
.regions .rl{font-size:12px;letter-spacing:.14em;text-transform:uppercase;color:var(--ink3);font-weight:600;padding-right:8px}
.regions .ch{font-size:14px;font-weight:600;text-align:center}.regions .ch small{display:block;font-weight:400;color:var(--ink3);font-size:12px}
.regions img{display:block;width:100%;border-radius:8px}
.regions .acc{text-align:center;font-size:clamp(15px,1.5vw,20px);font-weight:300}.regions .acc b{color:var(--blue);font-weight:400}
.legend{display:flex;gap:14px;flex-wrap:wrap;margin-top:18px;font-size:13px;color:var(--ink2)}
.legend i{display:inline-block;width:10px;height:10px;border-radius:2px;margin-right:6px;vertical-align:-1px}
.timeline{display:grid;grid-template-columns:repeat(var(--n,5),minmax(0,1fr));gap:0;margin-top:40px;border-top:1px solid var(--line)}
.timeline div{padding:18px 16px 0 0;min-width:0}
.timeline .w{font-family:var(--f-mono);font-size:12px;color:var(--ink3)}
.timeline b{display:block;font-size:17px;font-weight:600;margin:6px 0 4px}
.timeline span{font-size:15px;color:var(--ink2)}
.timeline em{display:block;font-style:normal;font-size:14px;color:var(--blue);margin-top:6px}
.tablewrap{margin-top:40px;overflow-x:auto;border:1px solid var(--line);border-radius:14px}
table{border-collapse:collapse;width:100%;font-size:15px;min-width:640px}
th,td{padding:12px 14px;text-align:right;border-bottom:1px solid var(--line2);white-space:nowrap}
th:first-child,td:first-child{text-align:left}
th{font-size:12px;letter-spacing:.12em;text-transform:uppercase;color:var(--ink3);font-weight:600}
tr.ca3 td{color:var(--blue)}tr.ca3 td:first-child{font-weight:600}
tr:last-child td{border-bottom:0}
.takeaways{display:grid;grid-template-columns:repeat(3,minmax(0,1fr));gap:26px;margin-top:40px}
.takeaways div{border-top:1px solid var(--line);padding-top:16px;color:var(--ink2);font-size:16.5px}
.film{margin-top:40px}.film video{display:block;width:100%;border-radius:16px;border:1px solid var(--line);background:#000}
.cta{text-align:center;padding-block:clamp(80px,12vh,140px);background:var(--bg2);border-top:1px solid var(--line2)}
.cta h2{font-size:clamp(34px,4.6vw,64px);font-weight:600;letter-spacing:-.028em}
.cta p{color:var(--ink2);font-size:clamp(18px,1.6vw,21px);max-width:44ch;margin:18px auto 0}
.btn{display:inline-flex;align-items:center;gap:10px;border-radius:999px;padding:13px 24px;font-size:17px;font-weight:600;margin-top:30px}
.btn.pri{background:var(--ink);color:#000}.btn.ghost{border:1px solid rgba(255,255,255,.3);color:var(--ink);margin-left:10px}
.notes{border-top:1px solid var(--line2)}.notes .wrap{padding-block:50px 56px;display:grid;grid-template-columns:repeat(3,minmax(0,1fr));gap:34px}
.notes h3{font-size:13px;letter-spacing:.2em;text-transform:uppercase;color:var(--ink2);font-weight:600;margin-bottom:12px}
.notes p,.notes li{font-size:13px;color:var(--ink3);line-height:1.6}.notes ul{margin:0;padding-left:18px}.notes .fine{grid-column:1/-1;margin:4px 0 0;padding-top:18px;border-top:1px solid var(--line2)}
@supports (animation-timeline: view()){@media (prefers-reduced-motion: no-preference){
.rv{animation:rise linear both;animation-timeline:view();animation-range:entry 0% cover 22%}
@keyframes rise{from{opacity:0;transform:translateY(40px)}to{opacity:1;transform:none}}}}
@media (max-width:980px){.specs{grid-template-columns:repeat(2,minmax(0,1fr))}.specs div{padding-bottom:20px}
.takeaways,.notes .wrap{grid-template-columns:minmax(0,1fr)}.timeline{grid-template-columns:repeat(2,minmax(0,1fr))}.timeline div{padding-bottom:18px}
.regions{grid-template-columns:repeat(3,minmax(0,1fr))}.regions .rl{grid-column:1/-1;padding-top:10px}.back{display:none}.pill{margin-left:auto}}
@media (max-width:620px){.pair,.pair.three,.charts,.split2{grid-template-columns:minmax(0,1fr)}.timeline{grid-template-columns:minmax(0,1fr)}
.regions{grid-template-columns:repeat(2,minmax(0,1fr))}.btn.ghost{margin-left:0}}
.when{font-size:14px;letter-spacing:.04em;color:var(--ink3)}</style>
<link rel="canonical" href="https://ca3.si/case_bci.html">
</head>
<body>
<header><div class="wrap"><a class="brand" href="index.html"><img src="ammonite_dark.svg" alt="">CA3</a>
<a class="back" href="index.html#cases">All use cases</a><a class="pill" href="index.html#pilot">Contact</a></div></header>
<section class="hero"><div class="wrap"><div class="head"><span class="eyebrow">Brain implant · SPINT decoder · FALCON H1 public recordings</span><h1>A brain-implant decoder learned seven new days. And kept the days it already decoded.</h1><p class="sub">SPINT, a published decoder for intracortical brain-computer interfaces, learned seven new days of a participant&#x27;s public recordings, one night at a time, with CA3 deciding what it learned and whether each night&#x27;s update stayed. The approved decoder never changes.</p><span class="when">Results recorded in November 2026</span></div><div class="media rv"><img src="bci_hero.jpg" alt="An illustration of the implant, and 30 seconds of what it records on the first day and on the last new day, from the same 176 channels" loading="lazy"></div><div class="specs rv"><div><span class="k">New days, R²</span><span class="v">0.283</span><span class="c">daily recalibration 0.252; ahead on 5 of 7 days</span></div><div><span class="k">Earlier days, R²</span><span class="v">0.939</span><span class="c">approved decoder 0.947; ordinary fine-tuning 0.712</span></div><div><span class="k">Nightly updates rolled back</span><span class="v">8 of 14</span><span class="c">under 0.01 lost on the earlier days, any night</span></div><div><span class="k">Approved decoder</span><span class="v">Identical</span><span class="c">before, during and after the run</span></div></div></div></section><section class="block"><div class="wrap"><div class="bh rv"><span class="verb ">Learns</span><h2>Each new day, one night at a time.</h2><p>What an implant records drifts from day to day. Each night the decoder learned from that day&#x27;s first session; the second session was the test. With CA3 it decoded the new days better than SPINT&#x27;s own daily recalibration on five of seven.</p></div><div class="wide rv"><img src="bci_learns.png" alt="Decoding each new day&#x27;s held-out session, daily recalibration against CA3, days 1 to 7" loading="lazy"></div><div class="kp rv"><div><b class="">0.283</b><span>mean R² on the new days, with CA3</span></div><div><b class="w">0.252</b><span>SPINT&#x27;s daily recalibration</span></div><div><b class="">5 of 7</b><span>days ahead of the recalibration</span></div></div></div></section><section class="block alt"><div class="wrap"><div class="bh rv"><span class="verb ">Keeps</span><h2>The earlier days stay.</h2><p>Retraining on the new days erases the old ones: ordinary fine-tuning on the same seven days dropped the 13 earlier sessions from 0.947 to 0.712. With CA3 they stayed at 0.939.</p></div><div class="wide rv"><img src="bci_keeps.png" alt="Decoding the 13 earlier sessions night by night: CA3 stays at 0.939, fine-tuning falls to 0.712" loading="lazy"></div><div class="kp rv"><div><b class="">0.939</b><span>earlier days with CA3; the approved decoder 0.947</span></div><div><b class="r">0.712</b><span>ordinary fine-tuning</span></div></div></div></section><section class="block"><div class="wrap"><div class="bh rv"><span class="verb r">Undoes</span><h2>It rolls back the nights that would harm.</h2><p>Every night&#x27;s update was checked against what the decoder must not lose, then kept or rolled back. Eight of the fourteen were rolled back, and on no night did the earlier days lose 0.01 or more.</p></div><div class="wide rv"><img src="bci_nights.png" alt="The 14 nightly updates, kept or rolled back, with the R² lost on the earlier days after each" loading="lazy"></div><div class="kp rv"><div><b class="">8 of 14</b><span>nightly updates rolled back by CA3</span></div><div><b class="">&lt; 0.01</b><span>lost on the earlier days, any night</span></div></div></div></section><section class="block alt"><div class="wrap"><div class="bh rv"><span class="verb g">Keeps the original</span><h2>It never touches the approved decoder.</h2><p>The fingerprint of the approved decoder, checked through the whole run, never changed. Going back to it is one step.</p></div><div class="fp"><div class="tablewrap rv"><table><thead><tr><th>Checked</th><th>Fingerprint of the approved decoder</th><th>Same</th></tr></thead><tbody><tr><td>Start</td><td>6bebdbfb7620f731</td><td>✓</td></tr><tr><td>After run 1</td><td>6bebdbfb7620f731</td><td>✓</td></tr><tr><td>After run 2</td><td>6bebdbfb7620f731</td><td>✓</td></tr><tr><td>End</td><td>6bebdbfb7620f731</td><td>✓</td></tr></tbody></table></div></div></div></section><section class="block"><div class="wrap"><div class="bh rv"><span class="verb ">Why it matters</span><h2>A decoder that changes every day is a medical device that changes every day.</h2><p>Regulators expect such changes to be planned in advance and verified against acceptance criteria set beforehand (in the US, a predetermined change control plan). With CA3, each day&#x27;s learning is one of those changes: checked against criteria fixed in advance, kept or rolled back, and on record.</p></div></div></section><section class="block alt"><div class="wrap"><div class="bh rv"><span class="verb ">How the test was run</span><h2>The test, step by step.</h2><p>Seven new days, one night each, and the field&#x27;s usual answers for comparison.</p></div><div class="timeline rv" style="--n:4"><div><span class="w">Before</span><b>The approved decoder</b><span>SPINT, public code, trained on 13 sessions over 6 days.</span></div><div><span class="w">Nights 1 to 7</span><b>One new day per night</b><span>Learned from the day&#x27;s first session; its second session is the test.</span></div><div><span class="w">Each night</span><b>The update is checked</b><span>Against what the decoder must not lose.</span><em>Kept, or rolled back if it would harm the earlier days</em></div><div><span class="w">Compared with</span><b>The field&#x27;s usual answers</b><span>SPINT&#x27;s own daily recalibration, and ordinary fine-tuning on the same days.</span></div></div><p class="fig">Measured: decoding (R²) on each new day&#x27;s second session, and on the 13 earlier sessions&#x27; held-out splits after the seven days. Pass criteria registered before the run: ahead of the recalibration by 0.02 or more on average and on at least 4 of 7 days, and no more than 0.01 lost on the earlier days. All three met.</p><div class="tablewrap rv"><table><thead><tr><th>Decoder</th><th>New days, mean R²</th><th>Days ahead of recalibration</th><th>Earlier days, R²</th><th>Nightly updates rolled back</th></tr></thead><tbody><tr><td>Original decoder</td><td>0.245</td><td></td><td>0.947</td><td></td></tr><tr><td>Daily recalibration (SPINT)</td><td>0.252</td><td></td><td>0.947</td><td></td></tr><tr><td>Ordinary fine-tuning</td><td>0.300</td><td>6 of 7</td><td>0.712</td><td>none (no control)</td></tr><tr class="ca3"><td>With CA3</td><td>0.283</td><td>5 of 7</td><td>0.939</td><td>8 of 14</td></tr></tbody></table></div><div class="wide rv"><img src="bci_all.png" alt="Decoding each new day: the original decoder, daily recalibration, CA3 and ordinary fine-tuning" loading="lazy"></div><div class="takeaways rv"><div>CA3 learned the new days better than the daily recalibration and kept the earlier days almost where they were.</div><div>Fine-tuning learned a little more, and lost a quarter of the earlier days.</div><div>The approved decoder was identical at the start and at the end.</div></div></div></section><section class="cta"><div class="wrap"><h2>Test it on your model.</h2><p>A pilot on your own decoder and recordings: you choose what it must never lose and what it should learn, and you measure the result on your own benchmark.</p><a class="btn pri" href="index.html#pilot">Contact</a><a class="btn ghost" href="index.html#cases">All use cases</a></div></section><section class="notes"><div class="wrap"><div><h3>Model and data</h3><ul><li>Data: FALCON H1, DANDI 000954 (CC-BY-4.0), intracortical recordings of a human participant.</li><li>Decoder: SPINT, public code, trained on 13 sessions over 6 days.</li><li>On top of the page: the first base day and the last new day, the same 176 channels in the same order, 30 seconds each, with the participant&#x27;s movement on top; the implant is an illustration.</li></ul></div><div><h3>Sources</h3><ul><li>Karpowicz BM, Ye J, Fan C, et al. Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark. NeurIPS 2024 Datasets and Benchmarks.</li><li>Le T, Fang H, Li J, Nguyen T, Mi L, Orsborn A, Sumbul U, Shlizerman E. SPINT: Spatial Permutation-Invariant Neural Transformer for Consistent Intracortical Motor Decoding. NeurIPS 2025.</li></ul></div><div><h3>Limits</h3><ul><li>One registered run (one seed), one decoder, one participant&#x27;s public data; earlier forms of the design were run twice before and are on record.</li><li>Two CA3 runs, each protecting half of the earlier days and read on the other half.</li><li>FALCON&#x27;s public sessions, not its official leaderboard.</li><li>About 4 hours on one GPU, decoder training included.</li></ul></div><p class="fine">Results from recorded, pre-registered tests. The mechanism is not shown. Model and dataset names are for identification only. Not produced or endorsed by the FALCON or SPINT authors. CA3 is developed by Alberto Acedo, PhD, at Biome Makers Inc.</p></div></section>
<script>
(function(){var still=window.matchMedia&&window.matchMedia('(prefers-reduced-motion: reduce)').matches;
var vids=[].slice.call(document.querySelectorAll('video.loop'));
if(still||!('IntersectionObserver' in window)){vids.forEach(function(v){v.controls=true;});return;}
var io=new IntersectionObserver(function(es){es.forEach(function(e){var v=e.target;if(e.isIntersecting){var p=v.play();if(p&&p.catch)p.catch(function(){v.controls=true;});}else v.pause();});},{threshold:0.3});
vids.forEach(function(v){io.observe(v);});})();
</script>
</body>
</html>