Artificial Neural Computing
169 subscribers
15 photos
3 videos
22 links
Download Telegram
We are accepting applications for our internship program. Extensive knowledge of mathematics, physics and machine learning is required.

Phase I (January 2023 - February 2023): Taking an online class on advanced topics in machine learning (e.g. statistical modeling, thermodynamic description, non-equilibrium dynamics, physics- and bio-inspired algorithms, etc.)

Phase II (March 2023 - April 2023): Working on a research project that involves modeling (biological, physical or machine) learning system using numerical methods (e.g. developing numerical simulations, statistical analysis of learning systems, etc.)

Phase III (May 2023 - June 2023): Working on a research project that involves modeling (biological, physical or machine) learning system using analytical methods (e.g. developing theory of learning, designing machine learning algorithms, etc.) 

If you have no experience, but a lot of knowledge we strongly encourage you to apply. If you have a lot of experience, but no knowledge we strongly discouraged you to apply.
https://artificialneuralcomputing.com/internship
πŸ‘7❀1πŸ”₯1
ANC Consulting LAB

(L)earning dynamics:
- Which machine learning algorithm is the best for a given learning task?
- How to generate initial conditions? 
- Which loss function should be used? etc.

(A)ctivation dynamics:
- Which neural architecture is the most appropriate for a given learning task? 
- How to execute activation map?
- Which activation functions should be used? etc.

(B)oundary dynamics:
- Which training data are most relevant for a given learning task?
- How to update the training data?
- Which data should be used for testing? etc.

To find out answers to these and other related questions, please fill out the form at https://artificialneuralcomputing.com/consulting
πŸ‘10❀1πŸ”₯1
Media is too big
VIEW IN TELEGRAM
This is a simulation of self-driving "cars", where each car is a separate neural network with only 30 neurons that learns to drive from scratch. Yes, with only 30 (!) neurons these cars learn how to drive better than most humans. Pay attention to how cars "discover" roundabouts, left- or right-hand traffic rules, etc. Sometime next week we will post a paper on arxiv explaining the theory behind this simulation. The theory is quite beautiful, and it teaches us not only how autonomous driving should be implemented, but also sheds light on how fundamental particles and biological organisms might have evolved in the context of the neural network theory.
πŸ‘6❀1πŸ”₯1
Next week we are launching theoretical machine learning journal club that would be open to all researchers (not only ANC staff and interns). Basically, we will meet every Wednesday at 11 am EST on Zoom to discuss research papers focusing on analytical rather than numerical results in machine learning theory. If you (or someone you know) are interested please join telegram group https://t.me/ANCJournalClub
πŸ‘5❀1πŸ”₯1
What do self-driving cars have to do with particle physics? A lot, actually. (Details in our new paper on arXiv https://arxiv.org/abs/2301.10077. Also check out the simulation https://artificialneuralcomputing.com/cars)
πŸ‘8❀1πŸ”₯1
We now have a YouTube channel where we post videos of lectures and journal club presentations on the theory of machine learning. Feel free to join:
https://www.youtube.com/@ArtificialNeuralComputing
πŸ‘10❀3πŸ”₯1
The World as a Neural Network

Are you curious about how the world operates like a neural network? Do you want to explore the implications of this idea? Our group meetings provide a platform for thought-provoking discussions of interdisciplinary topics such as the interconnectedness of systems and the emergence of complex behavior from simple rules. With a diverse group of individuals our meetings provide a unique opportunity to expand your knowledge, engage in stimulating discussions, and network with like-minded individuals.

Don't miss out on this chance; join us every Friday at noon EST via Zoom https://us06web.zoom.us/j/82683235624?pwd=WE1EbENwZXc0WkFyODU1Uk85YkZFdz09

YouTube videos of previous meetings: https://youtube.com/playlist?list=PLnu7tVik2MzKHBeqKy5nGWh5Hs5Wn2SX2

Facebook group: https://www.facebook.com/groups/2930104110608299

Telegram channel: https://t.me/theworldasaneuralnetwork and chat: https://t.me/theworldasaneuralnetworkchat
❀4πŸ‘3πŸ”₯1
NeuraPrint ver 1.0

We are thrilled to introduce NeuraPrint, our remarkable psychological tool meticulously designed to measure and explore the fundamental aspects of your free will. Immerse yourself in the enchantment as NeuraPrint utilizes a selection of relevant invariants to predict a "random" sequence generated by none other than you. But that's not all! We are currently developing an extraordinary feature to measure your level of consciousness. Prepare yourself for a mind-expanding adventure as we dive deep into the captivating realm of relevant invariants, analyzing their secrets to predict the sequence. Get ready for an awe-inspiring journey with NeuraPrint!

Download now from the App Store and Google Play.
πŸ”₯7❀1πŸ‘1
We are thrilled to announce the latest developments in our NeuraPilot project. We are excited to share that we have successfully implemented and are currently testing two of the three crucial components of self-driving technology:

1. Decision Making: Completed.
2. Vehicle Control: Completed.
3. Environment Detection: Work-in-progress.

To showcase the remarkable capabilities of NeuraPilot, we have created a captivating first-person view 3D and 360 videos. The simulation features twenty cars, each operating as a separate neural network. Remarkably, these neural networks consist of only fifty neurons, making efficient use of resources. The neural networks are trained from scratch, without any pre-training.

What sets our approach apart and enables our cars to learn quickly and effectively is our utilization of a small set of relevant invariants obtained through careful consideration of symmetries. For further information and details, please refer to our publication at https://arxiv.org/abs/2301.10077.
πŸ‘7πŸ‘4πŸ”₯2
We are delighted to present NeuraTutor, the cutting-edge educational platform revolutionizing the way we learn.

Matching: Enjoy tailored learning with our advanced AI tutor matching.

Assistance: Instant help from our 24/7 AI assistant.

Notifications: Stay updated on tutor/student matches and chat messages.

Accessibility: Seamlessly access NeuraTutor via web or mobile apps.

Join the NeuraTutor community today and unlock a world of educational possibilities!

Download the NeuraTutor app now from the App Store https://apps.apple.com/us/app/neuratutor/id6447997772 or Google Play https://play.google.com/store/apps/details?id=com.neuratutor.anc
πŸ‘6❀1πŸ”₯1
We're excited to announce our new website dedicated to the World as a Neural Network group, featuring a comprehensive Frequently Asked Questions section. Explore the interconnected world with us!

https://artificialneuralcomputing.com/wann
πŸ‘4❀3πŸ‘3
We are accepting applications for our 2024 internship program. Extensive knowledge of mathematics, physics and machine learning is required.

Phase I (January 2024 - February 2024): Taking an online class on advanced topics in machine learning (e.g. statistical modeling, thermodynamic description, non-equilibrium dynamics, physics- and bio-inspired algorithms, etc.)

Phase II (March 2024 - April 2024): Working on a research project that involves modeling (biological, physical or machine) learning system using numerical methods (e.g. developing numerical simulations, statistical analysis of learning systems, etc.)

Phase III (May 2024 - June 2024): Working on a research project that involves modeling (biological, physical or machine) learning system using analytical methods (e.g. developing theory of learning, designing machine learning algorithms, etc.) 

If you have no experience, but a lot of knowledge we strongly encourage you to apply. If you have a lot of experience, but no knowledge we strongly discouraged you to apply.
https://artificialneuralcomputing.com/internship
πŸ‘5❀1πŸ”₯1
Early Warning System for pandemics? Why not! https://arxiv.org/abs/2401.04444
πŸ‘8😒2❀1
Why do complex systems tend to exhibit critical behavior? The dataset-learning duality might be the answer. https://arxiv.org/abs/2405.17391
πŸ‘4❀1πŸ”₯1
πŸŽ‰ NeuraPrint 2.0 πŸŽ‰

Explore your mind like never before with NeuraPrint 2.0 β€” now available on iOS and Android!

Measure your Free Will and Consciousness with this unique tool:

🎲 Free Will: Determined by the accuracy of predictions of a 'random' sequence generated by the user.
🧠Consciousness: Calculated from the non-linearity of the predictions.

Ready to dive into self-discovery?

πŸ“² Get it on [iOS] (https://apps.apple.com/us/app/neuraprint/id6446124144)

πŸ“² Get it on [Android] (https://play.google.com/store/apps/details?id=org.anc.neuraprintapp.neuraprintapp)
πŸ‘3❀1πŸ”₯1
A study of the emergence of classical field theories from the activation and learning dynamics of neural networksβ€”whether artificial, biological, or fundamental. https://arxiv.org/abs/2411.08138
πŸ‘5❀1πŸ”₯1