Sunday, April 13, 2025

The Autoenconding of Forward Propagated Errors

 This might be a more neurally plausible model of biological systems. I do not know of any real biological systems that implement error backpropagation, the dominant algorithm in present day large language models and other machine learning approaches. 

Perhaps this is because artificial neural networks and AI took off from machine learning which in turn evolved from mathematical conception of minimizing loss functions. Specifically, loss functions generally focus on comparing predicted output with target output and then feeding this difference regressively rather than progressively. It makes sense from a practical and analytical point of view if evident speed of learning is the priority since the output layer determines output to be changed most immediately.

However, if we consider our muscles and how they are regulated by the neuromuscular synapse, it is difficult to apply how error is backpropogated there. The proposal is that error is only in sensors and this is forward propagated. Moreover, error in and of itself is meaningless to the system unless we assume that the system has a self state that is in non-equilibrium with the environment. It stands to reason that therefore forward propagated sensory errors must be integrated in an autoencoding operation to promote error signals consistent with the self and suppress those that are not. Thus, Hebbian learning remains the fundamental, as is observed in neurobiological findings.

Saturday, February 15, 2025

Personally Hosted Machine Intelligence

A big limitation now is that AIs are hosted on big commercial servers because only they have sufficient resources to build usable models. If intelligence and therefore capacity to utilize information is to become free as information is in principle (not only available to those with economic leverage), granted security and privacy issues, locally hosted machine intelligence (MI) is quintessential.

Saturday, February 01, 2025

The Higher Order Brain

The trained athletic brain learns to predict outcomes based on longer term projections from earlier sensations. Mathematically, this requires higher order derivatives. One wonders how this maps on to the quantization of basis states (eigen), in PCA.

Friday, January 31, 2025

Places to eat in Singapore and some other off the beaten track things

田雞粥

https://maps.app.goo.gl/jq4CbefYn2Xb5G5YA

牛肉河粉

https://maps.app.goo.gl/NVGavcCiFFhJ8oYn7

肉骨茶(比較非觀客的

https://maps.app.goo.gl/vWN8DsJmADhwzhF79

潮州粥

https://maps.app.goo.gl/EHLEuiWNhmFHzLzf6

印度燒餅(roti prata)

https://maps.app.goo.gl/mLmK5F3jx47nYZSw6

沙爹

https://maps.app.goo.gl/mLmK5F3jx47nYZSw6

Laksa

https://maps.app.goo.gl/TWtuctQe25emAQmh9

海南雞飯,魚粥,炒粿條,福建炒麵,等等 ————傳統美食街

https://maps.app.goo.gl/9xKJYUaKCQt2ycZw5

印度羊肉湯

https://maps.app.goo.gl/Cowhe8VQoPeou2naA

免費小朋友游泳池,大人便宜運動中心

https://maps.app.goo.gl/Y6S5ke34vTT98xdJ6

免費溜滑梯,租騎腳車,沙灘

https://maps.app.goo.gl/xoDw5j6W1mccFaPq7

國家蘭花館不貴,而蘭花真的很漂亮

https://maps.app.goo.gl/g3gZBj7XjN7XrXR36

在一般的美食街(不是Starbucks的飲料店),可是這點Kopi- O,或看你要喝什麼種的咖啡

https://naumihotels.com/singapore/blog-how-to-order-kopi-in-singapore/

中文版

https://www.thenewslens.com/article/111892