“Liquid” machine-learning system adapts to changing conditions | MIT News | Massachusetts Institute of Technology
MIT researchers developed a neural network that learns on the job, not just during training. The “liquid” network varies its equations’ parameters, enhancing its ability to analyze time series data. The advance could boost autonomous driving, medical diagnosis, and more.
The new type of neural network could aid decision making in autonomous driving and medical diagnosis. Daniel Ackerman | MIT News Office Publication Date : January 28, 2021 Press Inquiries Press Contact : Abby Abazorius Email: abbya@mit.edu Phone: 617-253-2709 MIT News Office Media Download ↓ Download Image Caption : MIT researchers have developed a neural “liquid” network that varies its equations’ parameters, enhancing its ability to analyze time series data. Credits : Image: Jose-Luis Olivares, MIT *Terms of Use: Images for download on the MIT News office website are made available to non-co
Explore this link on the map →related reading
- Researchers Discover a More Flexible Approach to Machine Learning | Quanta Magazinequantamagazine.org
- Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
- Trending Papers - Hugging Facepaperswithcode.com
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- NL.pdfabehrouz.github.io
- [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
- What is AI? Everything to know about artificial intelligence | ZDNETzdnet.com
- Continuous Thought Machinespub.sakana.ai
- [2404.19756] KAN: Kolmogorov-Arnold Networksarxiv.org
- Researchers Build AI That Builds AI | Quanta Magazinequantamagazine.org
- Deep Learning: Our Miraculous Year 1990-1991people.idsia.ch
- Machine learning - Wikipediaen.wikipedia.org