Fabrizio Musacchio · @pixeltracker
344 followers · 230 posts · Server sigmoid.socialThe #Wasserstein #metric (#EMD) can be used, to train #GenerativeAdversarialNetworks (#GANs) more effectively. This tutorial compares a default GAN with a #WassersteinGAN (#WGAN) trained on the #MNIST dataset.
#wasserstein #metric #emd #generativeadversarialnetworks #GANs #wassersteingan #wgan #mnist #machinelearning
Qiita - 人気の記事 · @qiita
36 followers · 962 posts · Server rss-mstdn.studiofreesia.com
ai-Paul E · @paul_ekwereii
31 followers · 53 posts · Server sigmoid.socialI experimented with using Large Language Models to solve a complex #imagerecognition problem.
The generated machine learning model by ChatGPT using a few prompts was able to detect #MNIST handwritten digits with an accuracy of 98%.
Read on if you want to learn how I did this.
#AI #artificialintelligence #deeplearning #neuralnetworks #bingai #bingchat #convolutionalneuralnetworks #LLMs #computervision
#imagerecognition #mnist #ai #artificialintelligence #deeplearning #neuralnetworks #bingai #bingchat #convolutionalneuralnetworks #LLMs #computervision
ai-Paul E · @paul_ekwereii
26 followers · 44 posts · Server sigmoid.socialUsing ChatGPT to solve the MNIST Image Recognition Problem with Deep Learning AI
#computervision #ChatGPT #OpenAI #NeuralNetworks #MNIST #PromptEngineering #ImageRecognition #DeepLearning #AI
#computervision #chatgpt #openai #neuralnetworks #mnist #PromptEngineering #imagerecognition #deeplearning #ai
Oliver Sampson · @oliversampson
120 followers · 920 posts · Server sigmoid.social@Sardonicus I d love to know how #ml algorithms trained on the #mnist dataset would perform with those images.
antonio vergari · @nolovedeeplearning
442 followers · 7 posts · Server ellis.social
It's hard to assess #Continual #Learning models and disentangle #hype from #progress, as the eval landscape is fragmented.
Even when learning from #MNIST to tiny #ImageNet (and back) #sota models tend to #catastrophic #forget a lot!
cc @ContinualAI
#continual #learning #hype #progress #mnist #imagenet #sota #catastrophic #forget
Shreyas Daniel · @shreydan
4 followers · 25 posts · Server sigmoid.social
Juliu · @juliu
47 followers · 362 posts · Server indieweb.socialMicrograd is very simple, only fully connected layers. So first trying to find out if it can even learn numbers based on MNIST dataset.
Then I hope to at least be able to verfit, so the essence works. Then I'll have the challenge of trying to make it work for every icon in the app.
Presumably I have to create/generate a huge set of icon images to train on..
#ux #micrograd #reactNative #MLP #MNIST #TinyUX #Karpathy #ai #NeuralNet
#neuralnet #ai #karpathy #TinyUX #mnist #mlp #reactnative #micrograd #ux
Tan Sing Kuang · @singkuangtan
0 followers · 14 posts · Server mstdn.social
Can you find a denoising deep learning algorithm better than mine?? Write in the comments... :blobcatthinksmart: :blobcatthinksmart: :blobcatthinksmart: #AIOverlord #deeplearning #mnist #AlgorithmsAreUs https://github.com/singkuangtan/BSautonet
#algorithmsareus #mnist #deeplearning #aioverlord
RecursiveNeuron :verified: · @RecursiveNeuron
102 followers · 132 posts · Server techhub.socialDeep learning series:
Project setup (CNN for MNIST)
#DeepLearning #MachineLearning #artificalintelligence #mnist
#deeplearning #machinelearning #artificalintelligence #mnist
Jane Adams · @janeadams
1184 followers · 247 posts · Server vis.social
Nothing like the #Kaggle #fashion #MNIST variant to make me feel like a real Elle Woods over here doing t-SNE on purses and saliency maps on ankle boots 😅
https://github.com/janeadams/fashion_model_analysis/
#MachineLearning #WomeninSTEM #AI #ML #tsne #pca #WiDS #Python
#python #wids #pca #tsne #ml #ai #womeninstem #machinelearning #mnist #fashion #kaggle
Albert Cardona · @albertcardona
697 followers · 557 posts · Server qoto.org
@ilennaj And you are the author of this most spectacular arXiv paper: "Can single neurons solve MNIST? the computational power of biological dendritic trees" Jones & Kording 2020 https://arxiv.org/abs/2009.01269 Hats off to you & @kordinglab ! And welcome.
#neuroscience #dendrites #MNIST
PS: subsequently published as "Might a Single Neuron Solve Interesting Machine Learning Problems Through Successive Computations on Its Dendritic Tree?" Jones & Kording 2021 https://direct.mit.edu/neco/article/33/6/1554/100576/Might-a-Single-Neuron-Solve-Interesting-Machine
#neuroscience #dendrites #mnist
Matt Hodges · @MattHodges
194 followers · 56 posts · Server mastodon.social
One of my favorite recent #projects (thanks @simon) was more around self-education. I wanted to dig deeper into #MachineLearning to see what I could do in vanilla Python — no PyTorch, no TensorFlow. Here's a #Jupyter Notebook where I implement a #ComputerVision #NeuralNetwork from scratch that classifies the #MNIST handwritten digits. The whole model trains in about 1 minute on my Intel MacBook CPU, and classifies with ~90% accuracy 🧠 I learned a lot! #DataScience
#projects #machinelearning #jupyter #computervision #neuralnetwork #mnist #datascience
Noah Williams · @noah_williams
17 followers · 325 posts · Server noc.socialWhoever invented the #mnist dataset needs to learn what quality control is.
#AI demystified: a decompiler
To prove that any "artificial neural network" is just a statistically programmed (virtual) machine whose model software is a derivative work of the source dataset used during its "training", we provide a small suite of tools to assemble and program such machines and a decompiler that reconstruct the source dataset from the cryptic matrices that constitute the software executed by them.
Finally we test the suite on the classic #MNIST dataset and compare the decompiled dataset with the original one.
#ArtificialIntelligence
#MachineLearning
#ArtificialNeuralNetworks
#microsoft
#GitHubCopilot
#Python
#StatisticalProgramming
#VectorMappingMachine
http://www.tesio.it/2021/09/01/a_decompiler_for_artificial_neural_networks.html
#ai #mnist #artificialintelligence #machinelearning #artificialneuralnetworks #microsoft #githubcopilot #python #StatisticalProgramming #VectorMappingMachine