Mastodawn

John Vaccaro (johniac)Mar 28, 2025

SciTech Chronicles. . . . . . . . .Mar 28th, 2025

#Prototaxites #Devonian #Rhynie #chitin #cellulose #delignifying #lye #diethylenetriamine #ACC #hyperglycemic #hippocampus #anhedonia #ANNs #fMRI #autoencoder #RSA #dairy #high-value #reuse #upcycle

SciTech Chronicles. . . . . . . . .Mar 28th, 2025

My best teacher is my last mistake. Vol II No 79 481 links Curated Fungus-like organism may be a completely unknown branch of life. https:...

AlexCrimi Jan 30, 2025

In pyramidal neuron we trust 🧠💡
Paper shows that dendritic #ANNs inspired by #brain connectivity reduce overfitting, use fewer parameters, and outperform traditional ANNs in image classification!
going towards #AI or towards cognitive #neuroscience? 🔥👇
https://www.nature.com/articles/s41467-025-56297-9

Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning - Nature Communications

Artificial neural networks, central to deep learning, are powerful but energy-consuming and prone to overfitting. The authors propose a network design inspired by biological dendrites, which offers better robustness and efficiency, using fewer trainable parameters, thus enhancing precision and resilience in artificial neural networks.

Nature

Mark May 28, 2023

“Just as #research has shown that feedback from caregivers shapes infant productions of sounds, feedback from the discriminator network shapes the sound productions of the generator network"

This is a pretty big finding. If it's accurate, we can test theories of #language development using artificial neural networks (#ANNs) instead of having to scan human brains!

#AI

https://www.quantamagazine.org/some-neural-networks-learn-language-like-humans-20230522/

Some Neural Networks Learn Language Like Humans | Quanta Magazine

Researchers uncover striking parallels in the ways that humans and machine learning models acquire language skills.

Quanta Magazine

katch wreck Apr 19, 2023

i predict that when #experiments show that single celled #organisms like #bacteria and #yeast can outperform overparametrized machine learning models like #ANNs on the most challenging types of decision problems, #biology will provide a strong riposte to #computer science and the mindset that biological #intelligence is easily explainable using #computational #models

#machineLearning #statistics #mathematical #models #ML #research #engineering #science #nature #complexity #theory #math #proof