GLASSR-Net: Glass Substrate Spectral Restoration Neural Network for Fourier Transform Infrared Microspectroscopy in the Fingerprint Region.
Anal. Chem. 2025
https://doi.org/10.1021/acs.analchem.4c06805
#infrared #neuralnets

This video will change your mind about Neural Networks - by Daniel Boctor

via Invidious:
https://inv.nadeko.net/watch?v=eCU2vQs0Q6s
(or YT: https://www.youtube.com/watch?v=eCU2vQs0Q6s)

Brilliant explainer video with great visualizations on how neural networks work.

According to Sepp Hochreiter (Linz) we are now at the end of the scaling up phase of AI. Subsequently, we move into the industrialization phase. Great morning keynote at the #NeurIPS2024 conference. #ArtificialIntelligence #NeurIPS #DeepLearning #AI #DataScience #NeuralNets

Excited to announce my 5th course, Network Algorithms and Approximations! Explore NP-complete problems (Set Cover, Unique Coverage, etc.), approximation techniques, and applications in data science, neural nets, & network optimization.

First lecture: https://youtu.be/Tnm-8xieqB4
Weekly uploads: Wednesdays at 7 PM EDT. Playlist: https://youtube.com/playlist?list=PLx7SjCaKZzEIeJxOlTuXveAE5eY7WOYB9

Plus, all 4 previous courses (Game Theory, Algorithms, Lower Bounds, Data Science) are online! https://youtube.com/@hajiaghayi

Wait, #LLMs or #NeuralNets can't reason!? This is so surprising! How could that happen!? This is unbelievable! I'm in shock!

But they surely have feelings, right...right!?

Deep learning folk should ban themselves from using the word "model" for a neural net! It makes scientific discussions really hard. Ecologist: "what is it a model of?" Physicist: "what is it a model of?" Empirical scientist: "Can I use this model in my model? What's our model of this model?"
.... Anyway: "network" is overloaded too, but as least "neural net" is pretty unambiguous (tho, I think, unfashionable). Let's neural net ("NN"). #deeplearning #terminology #academia #neuralnets

The Artificial Intelligence Papers

Original Research Papers With Tutorial Commentaries

https://jamesstone.sites.sheffield.ac.uk/books/theaipapers

Friend and colleague Jim Stone has a new book, with a "no mercy" cover and bomber content for understanding the technical foundations of the current AI moment

My seventh Math Research Livestream is now available on YouTube:

https://youtu.be/gKm-5vkb4yc

In this one I decided to pick up with where I ended the previous week, writing code for my discrete neural nets paper (https://arxiv.org/abs/2308.00677). This time I did actually get a decent amount of code written!

My next Math Research Livestream starts in about 30 minutes on Twitch! Check it out at https://www.twitch.tv/charlotteaten. I decided to pick up with where I ended last week, writing code for my discrete neural nets paper (https://arxiv.org/abs/2308.00677).

My sixth Math Research Livestream is now available on YouTube:

https://youtu.be/SN2zNj-CXdI

In this one I was coding live for the first time, since I needed to get back to the code for my discrete neural nets paper (https://arxiv.org/abs/2308.00677). I actually spent most of the time refamiliarizing myself with the state of the code and discussing the context of the work, but I did start on the task I had in mind near the end of the stream.

My next Math Research Livestream starts in about 30 minutes on Twitch! Check it out at https://www.twitch.tv/charlotteaten. I'm going to be coding live for the first time, since I need to get back to the code for my discrete neural nets paper (https://arxiv.org/abs/2308.00677).

https://youtube.com/watch?v=N6Piou4oYx8&si=GCCIjfppdsXXkh5d

Interesting to see where #NeuralNets are developing and how clever architectures can get competitive performance with Transformers - while reducing O(N^2) compute resources to O(log(N))

Multiplexed neuron sets make smaller optical neural networks possible

https://techxplore.com/news/2024-05-multiplexed-neuron-smaller-optical-neural.html

avail for #remote #contract #work

ideal lang: #Golang
ideal OS: #Linux or macOS

nice tech (tho optional) to have in the mix: #Docker, #Kubernetes, #AWS, #LLM, #NeuralNets, #NN, #AI

https://youtu.be/blaS5fBJdsE?si=gDWydTZgTPr138av

In the age of feverish activity about #NeuralNets this #ElectronMicroscopy video of 1 mm^3 of mouse #neurons is amazing!

What strikes me about real neuronal networks is not only the raw density of neurons (75,000 in 1 mm^3) but staggering connectivity and functional diversity of neural connections.

Data set from Allen Institute & co behind brain-map.org

Paper on the wiring of the mouse brain cube here: https://doi.org/10.1101/2021.07.28.454025

Neural nets combined with symbolic AI https://deepmind.google/discover/blog/alphageometry-an-olympiad-level-ai-system-for-geometry/
#ai #symbolicAI #neuralnets #alphageometry

You’re right, I totally forgot to include “hedgehog cheesecake hippopotamus” in that list. But I’m not sure that it would help in training a language model, since it isn’t a real word. At least, not in English. (Unless you live in the UK, in which case it might be.) ¯\_(ツ)\_(ツ)/¯ But yes, the point still stands. #trainingLLMs :) (P.S. Sorry for the typo in my previous reply. I meant “routine,” not “ritual.”) :) #neuralnets

I'm giving a short advertisement for my work on #NeuralNets at #JMM2024 in about 15 minutes! I applied a bit late and ended up in one of the contributed paper sessions. These are already a bit more subdued, but this one is particularly poorly attended. Perhaps it's for the best, since the videos on my YouTube channel (link in bio) are much more detailed than what I'm about to say.