Graph Attention Networks Veličković et al.: https://
arxiv.org/abs/1710.10903 #ArtificialIntelligence #DeepLearning #MachineLearning
MACHINE LEARNING
-
Graph Attention Networks: Advanced Deep Learning Architecture
By
–
-
Instruction Tuning for Large Language Models Survey
By
–
Instruction Tuning for Large Language Models: A Survey Zhang et al.: https://
arxiv.org/abs/2308.10792 #ArtificialIntelligence #CgatGPT #LargeLanguageModels -
What Criticisms Exist Against Machine Learning and AI?
By
–
What do they have against machine learning / ai?
-
Essential Skills for Tech Career Success and Leverage
By
–
Work on these skills: 1. Algorithms and data structures
2. Python
3. Databases
4. Machine learning
5. Distributed systems
6. Cloud computing
7. Talking to other people Don't need them all, but a combination of these will give you infinite leverage. -
Free MLOps Course by Andrew Ng on YouTube
By
–
Free Machine Learning In Production Course V/ @abacusai @AndrewYNg This is an excellent opportunity to learn MLOps!
100% Free on Youtube. Link: https://
youtube.com/playlist?list=
PLkDaE6sCZn6GMoA0wbpJLi3t34Gd8l0aK&feature=shared
…
[ Bookmark to use later ] #AI #GenerativeAI #ChatGPT #LLM #FutureOfWork #AI #MachineLearning -
Sea-thru: AI Algorithm Removes Water From Underwater Images
By
–
Thanks to a computer vision algorithm called Sea-thru, you can erase water from underwater images #Ai #ComputerVision Check out how this algorithm corrects the classic blue-green tint, revealing true, vibrant colors http://
spr.ly/6015PUA2f -
Complete Guide to Retrieval Augmented Generation Techniques
By
–
The Complete Guide to Retrieval Augmented Generation (RAG)@gopenai @Medium *********
Retrieval augmented generation (RAG) is an exciting technique that is transforming how natural language processing systems work. In this comprehensive guide, we’ll cover everything you need -
Neural Radiance Fields: ML meets Computer Graphics Education
By
–
It's a new enough area that there may not be books, but there are plenty of research papers, tutorials and open source implementations of things in the emerging area of Neural Radiance Fields (NeRFs). This would introduce them to ML in the context of computer graphics.
-
ML Environmental Impact: Prioritize Actual Data Over Misinformation
By
–
At the same time, the ML environmental impact community should use actual data whenever possible, and avoid wildly inaccurate estimates. There's a lot of misinformation and flawed data in the community that leads to wild headlines. Real data helps us focus on the right things!
-
ML Researchers Should Prioritize Energy Efficiency and Sustainability
By
–
I care about this topic as well. ML researchers should strive to use efficient algorithms and hardware, run computations in environmentally friendly data centers using locations with high CFE% energy, etc.
1/