Randy Kemp’s Post

It's well-known that some problems can be solved on the quantum computer exponentially faster than on the classical one in terms of computation time. However, there is more subtle way in which quantum computers are more powerful. There is a problem, which can be solved by quantum circuit of constant depth, but can't be solved by classical circuit of constant depth. In this notebook it consider this problem. https://lnkd.in/gBXdyFuz

How to confuse computer vision algorithm.

Top Important Computer Vision Papers for the Week from 01/07 to 07/07

At its core, an LLM OS is a natural language layer between humans and computational resources. But describing it that way barely scratches the surface. It’s akin to calling the internet “a way to share documents.” Technically true, but missing the point entirely. Traditional operating systems provide a file system, process management, and a graphical interface. An LLM OS, however, offers something far more profound: it enables you to express what you want in plain language and translates that intent into specific computer operations. Instead of learning to navigate complex software, you simply describe your goal, and the system interprets it for you.

The quality of #machinelearning model that can be trained on unsophisticated hardware is growing exponentially. Here's an example of a 70b LLM that can be trained on a standard consumer computer. #DataScience https://lnkd.in/e7V6MTB8

There is (probably) a universal speed limit (of a sort) to what computers can do.

#Can QML be used to fine-tune LLMs and deploy them on classical computers? Building on the Quantum-Train framework (or Quantum Parameter Generation) introduced earlier this year by our team, we propose Quantum Parameter Adaptation (QPA). This approach leverages QML to generate parameters for Parameter-Efficient Fine-Tuning (PEFT) methods tailored for LLMs. We applied QPA to fine-tune GPT-2 and Gemma-2B, focusing on PEFT techniques such as LoRA, DoRA, Prefix-tuning and Adapters. Our findings show that QPA not only reduces the number of trainable parameters in PEFT methods but also maintains—if not slightly improves—the performance of LLMs in text generation tasks. Since QPA uses quantum circuits solely for parameter generation, it avoids the challenges associated with quantum data encoding. Additionally, the resulting QPA fine-tuned model is a fully classical LLM, meaning it can be deployed on classical computers without requiring quantum resources during the inference stage. arXiv: https://lnkd.in/gu6cmdyB

🎉 Course Completion! 🎉 I’m thrilled to share that I’ve completed the Computer Vision Onramp course! 🎓 This course has equipped me with valuable skills in computer vision, including image processing, object detection, and feature extraction. It’s been an exciting journey, and I can’t wait to apply these skills to future projects! Big thanks to the course creators and everyone involved. Onward to more learning and growth! 🌟 #ComputerVision #MachineLearning #AI #TechSkills #LearningJourney #ArtificialIntelligence #ContinuousLearning

Learn the fundamentals of Computer vison on Deep-ML #machinelearning

The algorithm is the "how" LLM itself is not a scientific revolution It's just technological know-how and it will be figured out pretty quickly We already know it has three basic components Algorithm, Compute, and Data The process of getting there is the classic catch up, learn, iterate, reverse-engineer and improvise