#neuralnetwork — Public Fediverse posts

English – The Conversation | Self-driving cars struggle to see at night or in fog – but imitating the human brain can make them safe by Pablo Hernández Cámara, Profesor e investigador. Departamento de Ingeniería Electrónica & Laboratorio de Procesado de Imágenes, Universitat de València, Universitat de València

AI generated summary, Read the full article for complete information.

Self‑driving cars work well in clear daylight but become almost blind in darkness, rain or fog, because current AI vision systems lack the adaptive mechanisms that human eyes use. Researchers at the University of Valencia mimicked the brain’s “divisive normalisation”—a neuronal “volume‑control” that amplifies weak signals in dark scenes and attenuates bright ones—to modify standard AI models. Tests with real‑world European driving data, night‑time images from Switzerland and virtual simulators showed that the brain‑inspired models retained accurate object detection under fog and complete darkness, outperforming unmodified AI by more than 20 %. The study suggests that improving autonomous‑vehicle safety does not require larger computers or massive datasets, but rather can be achieved by borrowing evolution‑tested strategies from human vision, making AI systems more robust, adaptable, and trustworthy in all weather conditions.

Read more: https://theconversation.com/self-driving-cars-struggle-to-see-at-night-or-in-fog-but-imitating-the-human-brain-can-make-them-safe-282284

#UniversityofValencia #Selfdrivingcars #AIvision #Neuralnetwork #Humanbrain #Divisivenormalisation #Switzerland #Europeandatasets #Autonomousvehicles #Braininspired #

#Яндекс #Хуяндекс #NeuralNetwork #FAIL #screenshot

Из каментов с #пикабу​шечки...

One Open-source Project Daily

🦄 An Artificial Inteligence to teach Google's Dinosaur to jump cactus

https://github.com/ivanseidel/IAMDinosaur

#1ospd #opensource #artificialintelligence #dino #geneticalgorithm #genome #googledinosaur #neuralnetwork

One Open-source Project Daily

🦄 An Artificial Inteligence to teach Google's Dinosaur to jump cactus

https://github.com/ivanseidel/IAMDinosaur

#1ospd #opensource #artificialintelligence #dino #geneticalgorithm #genome #googledinosaur #neuralnetwork

One Open-source Project Daily

🦄 An Artificial Inteligence to teach Google's Dinosaur to jump cactus

https://github.com/ivanseidel/IAMDinosaur

#1ospd #opensource #artificialintelligence #dino #geneticalgorithm #genome #googledinosaur #neuralnetwork

One Open-source Project Daily

🦄 An Artificial Inteligence to teach Google's Dinosaur to jump cactus

https://github.com/ivanseidel/IAMDinosaur

#1ospd #opensource #artificialintelligence #dino #geneticalgorithm #genome #googledinosaur #neuralnetwork

One Open-source Project Daily

🦄 An Artificial Inteligence to teach Google's Dinosaur to jump cactus

https://github.com/ivanseidel/IAMDinosaur

#1ospd #opensource #artificialintelligence #dino #geneticalgorithm #genome #googledinosaur #neuralnetwork

Ez lett a végeredmény.

Nem jó, de nem is tragikus.
Az biztos, hogy a legutóbbi Claude által készítettnél informatívabb, edukatívabb, viszont vizuálisan eléggé katasztrófa és sok gombja nem is teljesen működik.

Viszont, sokkal jobban tanul, nem fagy ki, de amennyire nyomorodott, nem látni nagyon semmit belőle.

De, ez azzal az alap prompttal készül, amelyiket mindegyik modell megkap a teszt során. Ahhoz képest viszont jó!

Most akkor kicsit finomítok rajta, mert lehet ebből tényleg lehet személetes oktató anyag a végén. (Mindegyiknél ezt mondom, aztán néhány kör után megy a kukába mégis.)

#AI #ChatGPT #OpenAI #Claude #Anthropic #GPT #Opus #magyar #hungarian #neuron #neuron #háló #neuronháló #neural #neuralnetwork #network #magyar #hungarian

Kívácsi vagyok!

De eddig ez a GPT-5.5 valami nagyon... huhh...!

Előre blikkre nálam tényleg jobban teljesít, mint a Claude Opus-4.7!

Most kipróbáltatom vele a "szokásos" edukatív neuronhálós promptomat. Igazából, nálam ez az egyik összehasonlítási alapom.

Várom mi lesz belőle! Dolgozik vele rendesen, már több, mint tíz perce.

#AI #ChatGPT #OpenAI #Claude #Anthropic #GPT #Opus #magyar #hungarian #neuron #neuron #háló #neuronháló #neural #neuralnetwork #network #magyar #hungarian

🖥️ So you've decided to turn your prehistoric #Macintosh into a neural network powerhouse using HyperCard? 😂 Congratulations, you've reinvented the wheel by chipping away at it with a stone hammer! 🚀 Surely, the future of AI lies in 1989, just like your taste in technology! 🕰️
https://github.com/SeanFDZ/macmind #NeuralNetwork #HyperCard #AIInnovation #RetroTech #HackerNews #ngated

Talk on the discord about how much time it takes to process images with Darknet/YOLO. No need to guess and throw wild speculation -- run any of the built-in Darknet/YOLO tools and it will tell you exactly how long it takes at every step.

loading /home/stephane/nn/driving/set_04_dash/frame_064661.jpg
-> reading image from disk ........... 3.781 milliseconds [1280 x 720 x 3] [78.7 KiB]
-> resizing image to network dims .... 0.383 milliseconds [640 x 352 x 3]
-> using Darknet to predict .......... 2.581 milliseconds [7 objects]
-> using Darknet to annotate image ... 0.071 milliseconds [1280 x 720 x 3]
-> save output image to disk ......... 2.123 milliseconds [84.9 KiB]
-> total time elapsed ................ 9.324 milliseconds [107 FPS]

#Darknet #YOLO #ObjectDetection #NeuralNetwork

I don't talk about Darknet/YOLO much anymore on Mastodon. But I maintain the modern Darknet/YOLO repo.

This repo, written in C++ and CUDA, is used to analyze images and video frames to find objects. You train a neural network to identify things you need, and then you give it images or videos to inspect.

Darknet/YOLO is completely free. Uses the Apache 2 license.

The GitHub mirror is here: https://github.com/hank-ai/darknet/tree/v6-dev#table-of-contents

The main repo is here: https://codeberg.org/CCodeRun/darknet/src/branch/v6-dev#table-of-contents

An example image:
#Darknet #YOLO #NeuralNetwork #ObjectDetection

#NeuralNetwork #AIArt #ИБ #IT #ВеселыеКартинки #generated by #ChatGPT

Кибер-злодей Зеродей

Can you reverse engineer our neural network?

https://blog.janestreet.com/can-you-reverse-engineer-our-neural-network/

#HackerNews #reverseengineering #neuralnetwork #AIchallenge #machinelearning #techblog

Richard Russel posted a #BBCBASIC program for a #NeuralNetwork application (for #PatternRecognition) with a training dataset in the language's forum:

https://www.bbcbasic.net/forum/viewtopic.php?t=1825

#BASIC #AI #ArtificialIntelligence

Richard Russel posted a #BBCBASIC program for a #NeuralNetwork application (for #PatternRecognition) with a training dataset in the language's forum:

https://www.bbcbasic.net/forum/viewtopic.php?t=1825

#BASIC #AI #ArtificialIntelligence

Richard Russel posted a #BBCBASIC program for a #NeuralNetwork application (for #PatternRecognition) with a training dataset in the language's forum:

https://www.bbcbasic.net/forum/viewtopic.php?t=1825

#BASIC #AI #ArtificialIntelligence

Richard Russel posted a #BBCBASIC program for a #NeuralNetwork application (for #PatternRecognition) with a training dataset in the language's forum:

https://www.bbcbasic.net/forum/viewtopic.php?t=1825

#BASIC #AI #ArtificialIntelligence

Richard Russel posted a #BBCBASIC program for a #NeuralNetwork application (for #PatternRecognition) with a training dataset in the language's forum:

https://www.bbcbasic.net/forum/viewtopic.php?t=1825

#BASIC #AI #ArtificialIntelligence

@screwlisp @kentpitman regarding the discussion we had after the #LispyGopherClimate show ended, MiniKanren is logic programming language embedded in Scheme (sort-of like a Prolog implemented in Scheme and coded with S-expressions), and you can use machine leaning methods like neural networks to guide the search tree of the goal solver mechanism. This paper is an example of what I was talking about.

Even before LLMs were invented, MiniKanren was able to do program synthesis using purely symbolic logic. They developed a prototype called Barliman where you would provide example input->output pairs as constraints, and using a constraint solver, could generalize those examples to a function that generates any output for any input. As a simple example, you could give it the following input-output pairs:

1. () -> ()
2. (a) () -> (a)
3. () (a) -> (a)
4. (a) (a) -> (a a)

…and the constraint solver could determine that you are trying to implement the append function for lists and write the code automatically — without LLMs, using purely symbolic logic.

As you might expect, the solver could be very slow, or even diverge (never returning an answer). The paper I mentioned above talks about using neural networks to try to guide the constraint solver to improve the performance and usefulness of the results returned by the solver.

Now imagine applying this technique to other domains besides code generation or optimization, for example, auto-completion, or cache pre-fetching, and building it into a programmable computing environment like Emacs. You could have a tool like “Cursor,” but instead of using LLMs, it uses classical computing and constraint solvers, while taking a fraction of the amount of energy that LLMs use.

#tech #software #AI #LLM #MachineLearning #NeuralNetwork #ConstraintLogic #ConstraintSolver #LogicProgramming #Prolog #MiniKanren #Emacs #Lisp #Scheme #SchemeLang #ProgramSynthesis

#fediverse_ppl #смищно #Firefox #addons #ТрудностиПеревода #NeuralNetwork #userscript #Mastodon #MastodonTools

Лол, кек. Удивительно непонятное, но от этого иещеболее занятное взаимодействие переводчика, который (каюсь, грешен) иногда включаю в ленте, и юзерскрипта, чтобы комментировать кого-то вот прямо в ленте.

В комментарии — только 🚫 🤖— как напоминание о том, что @iron_bug не приемлет генерацию. Уважаю, позывы сдерживаю. Откуда берется такая интерпретация — совершенно непонятно. Пробовал добавлять тот же комментарий другим пользователям — не работает.

P.S. Сейчас у кого-то, кажется, подгорит на тему «мои посты отправляются на сервера гугла без моего ведома, а я всего-то хотела посрать на площади, прикрываяь ладошкой».

Блок через 5-4-3-2...

#Neuralnetwork finds an #enzyme that can break down #polyurethane
A completely new enzyme that researchers developed to break down polyurethane, the #polymer commonly used to make #foam cushioning, among other things. The new enzyme is compatible with an industrial-style recycling process that breaks the polymer down into its basic building blocks, which can be used to form fresh polyurethane.
https://arstechnica.com/science/2025/10/polyurethane-is-the-latest-polymer-broken-down-by-designer-enzymes/

#Neuralnetwork finds an #enzyme that can break down #polyurethane
A completely new enzyme that researchers developed to break down polyurethane, the #polymer commonly used to make #foam cushioning, among other things. The new enzyme is compatible with an industrial-style recycling process that breaks the polymer down into its basic building blocks, which can be used to form fresh polyurethane.
https://arstechnica.com/science/2025/10/polyurethane-is-the-latest-polymer-broken-down-by-designer-enzymes/

#Neuralnetwork finds an #enzyme that can break down #polyurethane
A completely new enzyme that researchers developed to break down polyurethane, the #polymer commonly used to make #foam cushioning, among other things. The new enzyme is compatible with an industrial-style recycling process that breaks the polymer down into its basic building blocks, which can be used to form fresh polyurethane.
https://arstechnica.com/science/2025/10/polyurethane-is-the-latest-polymer-broken-down-by-designer-enzymes/

Another reason why you really can't beat yourself up over mistakes in the past -

Human #brains have 5 distinct 'epochs' in a lifetime, study finds https://www.nbcnews.com/science/science-news/human-brains-5-epochs-development-rcna245663

#braindevelopment #research #neuroimaging #neuralnetwork #mentalhealth #brainarchitecture

#Mastodon #MastodonTools #виброкодинг #userscript #NeuralNetwork #Grok #ЯСделяль

Вотх, навиброкодил с помощью Grok (гопота не осилила, заковырявшись в простейшем алгоритме) юзерскрипет для #tampermonkey.

Алгоритм примерно такой: если вы смотрите на пост больше секунды (настраивается) — при прокрутке за границы экрана он скрывается.

Добавляется кнопочка показа / скрытия просмотренных постов.

ID 1000 последних постов запоминаются в локальном хранилище (после перезагрузки страницы всё равно не видны).

Потратил на пинание искусственных идиотов более шести часов (!). Подозреваю, что если бы знал жаваскрипт, управился бы за полтора, но поскольку кроме меня эта идея никому не пришла... Имеем то, что имеем. Пользуйтесь.

[Userscript для скрытия просмотренных постов.(]https://github.com/Johan-foreva/Mastodon-Hide-Read-Posts/blob/main/Mastodon%20Hide%20Read%20Posts%20(Logic%20Fixed)%205.9%20(Grok)-5.9.user.js)

Little update on my #neuralnetwork #experiment: Something happened. What happened is hard to say so far. The motionnet model was only trained on 3 videos for 2000 steps. One of the videos was a butterfly on a flower. (You can see it attached).

So this is the first actual test I've run successfully on the full pipeline. The prompt: A butterfly on a flower.

You can see the first frame (generated by #SDXL weights) and the generated #video.

Little update on my #neuralnetwork #experiment: Something happened. What happened is hard to say so far. The motionnet model was only trained on 3 videos for 2000 steps. One of the videos was a butterfly on a flower. (You can see it attached).

So this is the first actual test I've run successfully on the full pipeline. The prompt: A butterfly on a flower.

You can see the first frame (generated by #SDXL weights) and the generated #video.

#Mastodon #MastodonTools #дизигн #NeuralNetwork #виброкодинг #митол #CSS

Ура, при помощи #ChatGPT, такой-то матери и китайского блэка¹ (ЗБС, кстати) на фоне я зделол это!!!

Было — стало.

Заебись я хакир? 😉

¹ Кто торренты не котирует, вот вам стриминги и бандкампф.

Been messing around with a little #prototype #neuralnetwork. It behaves similarly to a #video #codec. It uses a frozen set of weights from #StableDiffusionXL and uses its latent space to carry forward to a set of networks that behave like the B-frame motion vectors used by codecs like #MPEG. These are smaller networks, letting me train it on my regular old #GPU while relying on the work of the big boys for generating I-frames via #SDXL.

At least that's the theory. Reality remains to be seen.

Been messing around with a little #prototype #neuralnetwork. It behaves similarly to a #video #codec. It uses a frozen set of weights from #StableDiffusionXL and uses its latent space to carry forward to a set of networks that behave like the B-frame motion vectors used by codecs like #MPEG. These are smaller networks, letting me train it on my regular old #GPU while relying on the work of the big boys for generating I-frames via #SDXL.

At least that's the theory. Reality remains to be seen.

Since #Xbox hardware is pretty much dead, #AMD decides to move all its chips with #Sony and #PlayStation6.

https://www.youtube.com/watch?v=ItXPvGrI6gY

I'll thread lightly on this hardware announcement. They usually overpromise and underperform. Wouldn't be surprised if it turns out this way... again.

#Videogames #Gaming #Games #ProjectAmathyst #Sony #PlayStation #PlayStation6 #PS6 #MachineLearning #AI #ArtificialIntelligence #ML #FSR #PSR #NeuralNetworks #NeuralNetwork #NPU #SoC #Technology #Hardware #PCHardware

Ah, the 'Univariate Gaussian Mixture Model Neural Network' – because nothing screams "cutting edge" like a bunch of math-y gibberish wrapped in buzzword salad 🥗🤖. Thanks to the Simons Foundation for funding this thrilling adventure in #overcomplication. Remember folks, the future is bright... and also incomprehensible! 🌟💡
https://arxiv.org/abs/2509.07569 #UnivariateGaussianMixtureModel #NeuralNetwork #MathBuzzword #SimonsFoundation #FutureTech #HackerNews #ngated

#Mastodon #MastodonTools #GlitchSoc #виброкодинг #ChatGPT #NeuralNetwork

ВАРНИНГ! Всё ниже написанное актуально только для серверов с glitch-soc, тем, кто сидит на ванильке, можно не читать.

А остальные — признайтесь, кого не бесит лишний клик при добавлении картинки? Ведь никто не пользуется этой дудль-рисовалкой, реально.

Поэтому, покумекав, родили такой скрипт для #Tampermonkey

// ==UserScript==
// @name         Button triggers LI click & hide menu
// @description  Button triggers LI click & hide menu
// @version      0.1
// @match        https://cr8r.gg/*
// @match        https://tilde.zone/*
// @match        https://infosec.exchange/*
// @match        https://expressional.social/*
// @match        https://toot.cat/*
// @run-at       document-idle
// ==/UserScript==

(function() {
    'use strict';

    // Интервал для поиска кнопки
    const buttonInterval = setInterval(() => {
        const button = document.querySelector('.compose-form__upload-button button');
        if (button) {
            clearInterval(buttonInterval);
            // console.log('Button found!');

            // Навешиваем обработчик на кнопку
            button.addEventListener('click', () => {
                // console.log('Button clicked, waiting for LI...');

                // Создаём MutationObserver на body
                const observer = new MutationObserver(mutations => {
                    for (const mutation of mutations) {
                        for (const node of mutation.addedNodes) {
                            if (node.nodeType === 1) { // только элементы
                                const li = node.querySelector('li[data-index="upload"]');
                                if (li) {
                                    // Скрываем родительский div
                                    const container = li.closest('div');
                                    if (container) container.style.display = 'none';
                                    // console.log('Upload menu hidden immediately!');

                                    // Вызываем клик на li
                                    li.click();
                                    // console.log('LI clicked automatically!');

                                    // Отключаем observer
                                    observer.disconnect();
                                    return;
                                }
                            }
                        }
                    }
                });

                // Наблюдаем только за вставкой новых узлов
                observer.observe(document.body, { childList: true, subtree: true });
            });
        }
    }, 250); // ищем кнопку каждые 250 мс

})();

Он что делает: обрабатывает клик по кнопке добавления медии, скрывает менюшку с выбором и сам «кликает» на добавление картинки. Мелочь (да какая, к черту, мелочь — дико бесит же, ну!), а приятно.

#Anthropic researchers studied how #AI systems’ #personalities change and what makes them #evil. They found that #data influences an AI model’s #qualities, and by identifying which parts of the #neuralnetwork correspond to specific traits, they could predict and control these impulses: flagging problematic data and injecting undesirable traits. https://www.theverge.com/anthropic/717551/anthropic-research-fellows-ai-personality-claude-sycophantic-evil?eicker.news #tech #media #news

#userscript #MastodonTools #вдогонку #NeuralNetwork

У-у-ухъ!

Код не читай — сразу запускай! 😡

Отсутствие контроля за говном, написанным ИИшницей, которое было «похоже на правду» — только что стоило мне проебанного длиннопоста на пол-экрана 😭

Причем. Самое блядство — это то, что написано было там В точности наоборот относительно того, что я просил! 😤 Причем зловредный кусок кода был не нужен!

А в итоге? Виноват-то всё равно мясной им не стыдно, зато токенов наелись... 🍖

A Neural Net For a Graphing Calculator? https://hackaday.com/2025/07/17/a-neural-net-for-a-graphing-calculator/ #ArtificialIntelligence #graphicscalculator #texasinstruments #MachineLearning #handheldshacks #neuralnetwork #calculator #ti-84

A Neural Net For a Graphing Calculator? - Machine learning and neural nets can be pretty handy, and people continue to push ... - https://hackaday.com/2025/07/17/a-neural-net-for-a-graphing-calculator/ #artificialintelligence #graphicscalculator #texasinstruments #machinelearning #handheldshacks #neuralnetwork #calculator #ti-84

🥳 Happy to share that we (well, Luxembourg Institute of Science and Technology (LIST)) have now become an OMG member

Our immediate goal is to contribute to the #Portability and #Interoperability of Neural Networks #RFP and propose our #neuralnetwork #metamodel as the basis for that.

Looking forward to collaborating with other companies to improve / merge / expand our view on #modeling neural networks💪💪 and helping organizations #migrate and #exchange their network definitions.

The #NN metamodel is implemented in BESSER.

Read more about our proposal ⬇️⬇️⬇️

https://modeling-languages.com/modelling-neural-network-models/

Teaching a Commodore 64 to “Think” — ProjectCD.Chronicles Pulls It Off in BASIC
#C64 #RetroComputing #NeuralNetwork #ProjectCDChronicles #BASICProgramming #Commodore64 #8bitAI #PatternRecognition
https://theoasisbbs.com/teaching-a-commodore-64-to-think-projectcd-chronicles-pulls-it-off-in-basic/?feed_id=3043&_unique_id=6810d028ad1e3

🤖💦 A neural network that turns your model's output into a Jackson Pollock masterpiece! 🎨 Because what we REALLY needed was an #AI that doodles in liquid memory, right?! 😂
https://github.com/babycommando/neuralgraffiti #Art #NeuralNetwork #JacksonPollock #CreativeDoodles #LiquidMemory #HackerNews #ngated

#MastodonTools #JavaScript #userscript #Firefox #TamperMonkey #NeuralNetwork #ChatGPT

Господамы, #вопрос: у вас ведь тоже в вебмордии #Mastodon при включенной «медленной загрузке» (когда ленту обновлять вручную надо) она чаще всего «съзжает», да? Это же ведь не у одного меня такая беда?

Кто как борется с этим? А то, может, я зря сижу скрипт пилю и всё проще решается? 🤔

@rf
@ru
@Russia
@russian_mastodon

You can tell a lot about a person by looking into their eyes, more specifically, retinal scans offer non-invasive views of the central nervous and circulatory systems and can diagnose non-ocular diseases like Parkinson's even before symptoms.

https://researchinenglish.com/article/2025.2/new-retinal-scan-ai-finds-disease-indicators-c53gok7m?utm_source=mastodon&utm_medium=social

#research #news #eyes #medicine #retina #centralnervoussystem #retina #retinascan #AI #neuralnetwork #preprint #paper

Earth's Oceans Are Filled With What Scientists Are Calling ‘Dark Vessels’ | Satellite Mapping Reveals Extensive Industrial Activity At Sea
--
https://www.earth.com/news/dark-vessels-most-industrial-fishing-activity-is-not-publicly-tracked/ <-- shared technical article
--
https://doi.org/10.1038/s41586-023-06825-8 <-- shared paper
--
https://dialogo-americas.com/articles/chinas-rampant-illegal-fishing-is-endangering-the-environment-and-the-global-economy/ <-- shared opinion piece
--
#GIS #spatial #mapping #remotesensing #satellite #illegalfishing #tracking #AI #statesponsored #deeplearning #darkvessels #GPS #transmitters #AIS #turnedoff #maritime #marine #vessels #foodsecurity #sustainability #global #globalsecurity #transponders #smuggling #illegal #commercialfishing #transport #energy #oil #gas #shipping #resources #Sentential #Sentential1 #spatialanalysis #spatiotemporal #realtime #model #modeling #neuralnetwork #accuracy #radar #SAR #cargoship #infrastructure #ocean #worldwide #humanrights #MPAs #coast #coastal #EEZs #tankers #industrial #sea #windfarms

#Radeon are not even in the benchmarks for #RayTracing against the #RTX5090, rofl.

https://www.youtube.com/watch?v=Q82tQJyJwgk

But... seems that the card is for people who CAN spend a $2,000.

#NVIDIA #GeForce #RTX #RTX5000 #Blackwell #Hardware #PC #PCHardware #Computer #Computers #Videogames #Gaming #Games #PathRatrcing #DLSS #DLSS4 #GraphicsCard #GPU #dGPU #AI #ArtificialIntelligence #ML #MachineLearning #CUDA #NeuralNetwork #CUDACores #TensorCores #LLM #LanguageModel #LM #Benchmarks #Review #Technology #TOPS

Training 5 different LSTM models with Python3, PyTorch, and FreeBSD. I turned off X to reclaim more resources during model training. Since I did not know how to screen capture in CLI mode, let's settle with phone's camera. #LSTM #FreeBSD #NeuralNetwork

Training 5 different LSTM models with Python3, PyTorch, and FreeBSD. I turned off X to reclaim more resources during model training. Since I did not know how to screen capture in CLI mode, let's settle with phone's camera. #LSTM #FreeBSD #NeuralNetwork

Going Digital: Teaching a TI-84 Handwriting Recognition https://hackaday.com/2024/12/24/going-digital-teaching-a-ti-84-handwriting-recognition/ #convolutionalneuralnetwork #ArtificialIntelligence #graphicscalculator #texasinstruments #MachineLearning #handheldshacks #neuralnetwork #handwriting #TI-84PlusCE #calculator #mnist #ti-84 #News

Going Digital: Teaching a TI-84 Handwriting Recognition https://hackaday.com/2024/12/24/going-digital-teaching-a-ti-84-handwriting-recognition/ #convolutionalneuralnetwork #ArtificialIntelligence #graphicscalculator #texasinstruments #MachineLearning #handheldshacks #neuralnetwork #handwriting #TI-84PlusCE #calculator #mnist #ti-84 #News

Going Digital: Teaching a TI-84 Handwriting Recognition https://hackaday.com/2024/12/24/going-digital-teaching-a-ti-84-handwriting-recognition/ #convolutionalneuralnetwork #ArtificialIntelligence #graphicscalculator #texasinstruments #MachineLearning #handheldshacks #neuralnetwork #handwriting #TI-84PlusCE #calculator #mnist #ti-84 #News