Future Directions in Artificial Intelligence (13.5)
Вставка
- Опубліковано 11 лип 2024
- In this video I conclude the course and discuss some future AI directions.
Code for This Video:
github.com/jeffheaton/app_dee...
~~~~~~~~~~~~~~~ COURSE MATERIAL ~~~~~~~~~~~~~~~
📖 Textbook - Coming soon
😸🐙 GitHub - github.com/jeffheaton/app_dee...
▶️ Play List - • 2023 PyTorch Version A...
🏫 WUSTL Course Site - sites.wustl.edu/jeffheaton/t8...
~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~
🖥️ Website: www.heatonresearch.com/
🐦 Twitter - / jeffheaton
😸🐙 GitHub - github.com/jeffheaton
📸 Instagram - / jeffheatondotcom
🦾 Discord: / discord
▶️ Subscribe: ua-cam.com/users/heatonresea...
~~~~~~~~~~~~~~ SUPPORT ME 🙏~~~~~~~~~~~~~~
🅿 Patreon - / jeffheaton
🙏 Other Ways to Support (some free) - www.heatonresearch.com/suppor...
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#MachineLearning #DataScience #PatternRecognition #PredictiveModeling #DataDrivenDecisions #MLTutorials #DataAnalysisTips - Наука та технологія
Forward-Forward potentially can replace backpropagation and gradient descent.
My prediction for 2024 is that we'll remember it as the year of AI Agents!
When you say things are changing at the speed of light, are you referring to the speed of light in a vacuum? Water? Or perhaps some other medium. Thank you
;-) As an observer, in a vacuum, traveling 90% the speed of light with a headlight on. Lol.
The speed of light at the end of the tunnel. Which is the speed of a freight train.
I think reasoning is the next phase after maybe using synthetic data to train new AI's.
I think MAMBA or something similar will give the transformer some competition. The AI winter is over, and now the money is focused back to AI. FunSearch for mathematics looks promising as well. Oh! and adding some reoccurrence back into the transformer and other modifications that will be done outside of OpenAI. 2024 is going to be exciting as we take our apps from the workbench to the desktops.