In retrospect, this interview with Geordie Rose I recorded in 2013, has turned out to be prophetic: Geordie Rose: Machine Learning is Progressing Faster Than You Think https://lnkd.in/dkTVTwB
Nikola Danaylov Ⓥ’s Post
More Relevant Posts
-
PyTorch can be extremely intimidating. It simultaneously allows for both low-level and high-level operations. The learning curve for PyTorch is steep primarily because you need to know AI fundamentals like: - Neural network architectures - Learning algorithms - Linear algebra and matrix operations While also knowing: - PyTorch-specific concepts, like its implementation of dynamic computation graphs and tensor operations - GPU acceleration and parallel computing - Memory management (for large datasets) For someone just starting out, it can be pretty intense. That’s why it’s nice to see frameworks like TinyGrad that implement the basics really cleanly, so you can focus on learning. All you really need is an autograd/tensor library and an optimizer.
To view or add a comment, sign in
-
A new field promises to usher in a new era of using machine learning and computer vision to... | Click below to read the full article at The Digital Insider.
The Role of Machine Learning and Computer Vision in Imageomics – Technology Org
https://thedigitalinsider.com
To view or add a comment, sign in
-
A new field promises to usher in a new era of using machine learning and computer vision to... | Click below to read the full article at The Digital Insider.
The Role of Machine Learning and Computer Vision in Imageomics – Technology Org
https://thedigitalinsider.com
To view or add a comment, sign in
-
This novel approach to machine learning using just one qubit highlights that we can often benefit from taking a fresh look at how to implement a solution rather than simply porting our existing approach to a new technology. https://lnkd.in/emXNW2aN
Single Qubit Breakthrough: Solving Classical Machine Learning Problems with Quantum Efficiency
http://quantumzeitgeist.com
To view or add a comment, sign in
-
Very interesting article on Explainable Artificial Intelligence!
A review of Explainable Artificial Intelligence in healthcare
sciencedirect.com
To view or add a comment, sign in
-
A very interesting article about the birth of AI. The term “machine learning” was first used in 1959
The “birth of AI”. 1956. John McCarthy (Dartmouth), Marvin Minsky (Harvard), Nathaniel Rochester (IBM) and Claude Shannon (Bell Labs). Of course, this might not have been possible without Ada Lovelace writing the world’s first computer program. https://lnkd.in/exHwkEND
Dartmouth Summer Research Project: The Birth of Artificial Intelligence - History of Data Science
historyofdatascience.com
To view or add a comment, sign in
-
When I try to break down the concepts of computer science in activities and workshops for young students, it is easy to see and use situations from everyday life. The complex world of computing is replicated in every corner, in every place of our world. Understanding how the world works will certainly help us develop better computational skills and become better digital citizens. The role of computer science is fundamental.
Does the complex world around us leave you feeling overwhelmed? 🫠 This piece highlights the importance of learning computer science (CS) to develop computational thinking skills. By doing so, we can not only tackle some of our most challenging problems but also harness the power of AI to find solutions. ➡️ What are your thoughts on this article? (📝 : Lance Fortnow) https://lnkd.in/gDEjynsp
Everything You See Is a Computational Process, If You Know How to Look
wired.com
To view or add a comment, sign in
-
Great work is often not recognized or appreciated in the moment. Such was the case of the support vector machine (SVM), the crown jewel of classical machine learning. Here is the story ... Way back in 1964, in the then U.S.S.R, Vladimir Vapnik and Alexey Chervonenkis invented a classification method based on maximum margin hyperplanes. That was a whopping four decades before the era of fast GPU processors which ushered in the deep learning era. In 1990, Vapnik immigrated to the United States to work at AT&T Bell labs. There, he collaborated with Bernhard Bohser and Isabella Guyon, to apply the "kernel trick" to his 1964 maximum margin hyperplane method, thereby yielding the powerful support vector machine we know today. Excited about this great new discovery, in 1992 Vapnik submitted 3 papers describing the SVM to NeurIPS, the premier machine learning conference. All 3 papers were very swiftly rejected by the reviewers. Today, the SVM stands as a towering monument in the world of classical machine learning, bridging powerful ideas, frameworks, and eras. It turned out that the reviewers were squarely wrong. Great work is often not recognized or appreciated in the moment. If you are working on something today and are not getting the recognition and support you believe your work deserves, think of Vapnik and keep going. You are in good company. ---- Stay tuned for the entire video series of all 20 chapters from my book "The Foundational Mathematics of Artificial Intelligence." See comments for details. #ArtificialIntelligence #Mathematics
To view or add a comment, sign in
-
Our Chief Science Officer Román Orús is representing Multiverse Computing this week at Big Data & AI World 2024 in London. Roman is speaking in two sessions: CompactifAI: Extreme Compression of LLMs and Quantum Inspired: The Path to Quantum Computing. Tensor networks will be a highlight of both talks as Roman explains how this mathematical framework can be used to build advanced optimizers and a variety of machine learning models. Stop by our Stand at B351 to learn more about CompactifAI, our compressor for large language models, and Singularity, our quantum software platform. #AI #ML #QML #bigdata #quantumcomputing
To view or add a comment, sign in
-
The role of machine learning and computer vision in Imageomics
The role of machine learning and computer vision in Imageomics
sciencedaily.com
To view or add a comment, sign in
Yeah, I was right I guess :-)