Machine Learning (ML) is known as the high-interest credit card of technical debt. It is relatively easy to get started with a model that is good enough for a particular business problem, but to make that model work in a production environment that scales and can deal with messy, changing data semantics and relationships, and evolving schemas in an automated and reliable fashion, that is another matter altogether. If you’re interested in learning more about a few well-known ML platforms, you’ve come to the right place!
As little as 5% of the actual code for machine learning production systems is the model itself. What turns a collection of machine learning solutions into an end-to-end machine learning platform is an architecture that embraces technologies designed to speed up modelling, automate the deployment, and ensure scalability and reliability in production. I talked about lean D/MLOps, data and machine learning operations, before, because machine learning operations without data is pointless, so an end-to-end machine learning platform needs a holistic approach. Read More
Daily Archives: August 24, 2021
How to avoid machine learning pitfalls: a guide for academic researchers
This document gives a concise outline of some of the common mistakes that occur when using machine learning techniques, and what can be done to avoid them. It is intended primarily as a guide for research students, and focuses on issues that are of particular concern within academic research, such as the need to do rigorous comparisons and reach valid conclusions. It covers five stages of the machine learning process: what to do before model building, how to reliably build models, how to robustly evaluate models, how to compare models fairly, and how to report results. Read More
#performanceHow a Simple Crystal Could Help Pave the Way to Full-Scale Quantum Computing
Vaccine and drug development, artificial intelligence, transport and logistics, climate science—these are all areas that stand to be transformed by the development of a full-scale quantum computer. And there has been explosive growth in quantum computing investment over the past decade.
Yet current quantum processors are relatively small in scale, with fewer than 100 qubits— the basic building blocks of a quantum computer. Bits are the smallest unit of information in computing, and the term qubits stems from “quantum bits.”
While early quantum processors have been crucial for demonstrating the potential of quantum computing, realizing globally significant applications will likely require processors with upwards of a million qubits.
Our new research tackles a core problem at the heart of scaling up quantum computers: how do we go from controlling just a few qubits, to controlling millions? In research published today in Science Advances, we reveal a new technology that may offer a solution. Read More
OpenAI Codex Live Demo
Using Artificial Intelligence in the VFX and Film Industry
I’ll agree with everyone straight off the bat. This is a scary topic. Even more so once you consider this will be a huge part of our overall future. I think its a good idea to recognize what type of technology we will need to prepare ourselves for. So this is what this article is going to be about. Just plan research, and the pros and cons of AI. Read More
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
The Super-Resolution Generative Adversarial Network (SRGAN) [1] is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts. To further enhance the visual quality, we thoroughly study three key components of SRGAN – network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN). In particular, we introduce the Residual-in-Residual Dense Block (RRDB) without batch normalization as the basic network building unit. Moreover, we borrow the idea from relativistic GAN [2] to let the discriminator predict relative realness instead of the absolute value. Finally, we improve the perceptual loss by using the features before activation, which could provide stronger supervision for brightness consistency and texture recovery. Benefiting from these improvements, the proposed ESRGAN achieves consistently better visual quality with more realistic and natural textures than SRGAN and won the first place in the PIRM2018-SR Challenge [3]. Read More
#gans, #image-recognition
Rick's Cafe AI 