Note: This section of the site is under heavy construction, tread carefully.

Bookmarks tagged with “machinelearning”

72 bookmarks by garrettc


How DALL·E 2 Works

"DALL·E 2 is a system for text-to-image generation developed by my coauthors and me at OpenAI. When prompted with a caption, the system will attempt to generate a novel image from scratch that matches it."

Bookmarked on #


DALL·E 2

"DALL·E 2 is a new AI system that can create realistic images and art from a description in natural language."

Bookmarked on #


Pangur

Pangur is a visual programming language for working with text in real time.

Bookmarked on #


This City Does Not Exist

ML generated satellite shots of non-existant cities.

Bookmarked on #



Cheezam ! By Prevision.IO - Computer Vision with AI for cheese

"…can machine learning be used to identify a type of cheese?"

Bookmarked on #



Maiahi Bot (@maiahibot) / Twitter

Tag it in a Tweet containing an image, and it will reply with a version of the same image turned into a little animation which sings the Maiahi song.

Bookmarked on #


Can you guess it?

Two artificial neural networks generated posters while thinking of famous movies. Can you guess which movie it is?

Bookmarked on #



This Meme Does Not Exist

Memes Generated by an Artificial Neural Network

Bookmarked on #


Failure Modes in Machine Learning

"In the last two years, more than 200 papers have been written on how Machine Learning (ML) can fail because of adversarial attacks on the algorithms and data; this number balloons if we were to incorporate non-adversarial failure modes. The spate of papers has made it difficult for ML practitioners, let alone engineers, lawyers and policymakers, to keep up with the attacks against and defenses of ML systems. However, as these systems become more pervasive, the need to understand how they fail, whether by the hand of an adversary or due to the inherent design of a system, will only become more pressing."

Bookmarked on #






Pattern Radio: Whale Songs

Use AI to explore thousands of hours of humpback whale songs and make your own discoveries

Bookmarked on #



Automated Keyword Extraction from Articles using NLP

"Conventional approaches of extracting keywords involve manual assignment of keywords based on the article content and the authors’ judgment. This involves a lot of time & effort and also may not be accurate in terms of selecting the appropriate keywords. With the emergence of Natural Language Processing (NLP), keyword extraction has evolved into being effective as well as efficient. And in this article, we will combine the two — we’ll be applying NLP on a collection of articles (more on this below) to extract keywords."

Bookmarked on #


A People's Guide to AI

"Systems that use artificial intelligence are quietly becoming present in more and more parts of our lives. But what does this technology really mean for people, both right now and in the future?"

Bookmarked on #


Practical AI

A practical approach to learning machine learning with Python and notebooks.

Bookmarked on #


Arbitrary Image Stylization in the Browser

"…an implementation of an arbitrary image stylization algorithm running purely in the browser using TensorFlow.js. As with all neural style transfer algorithms, a neural network attempts to "draw" one picture, the Content (usually a photograph), in the style of another, the Style (usually a painting)."

Bookmarked on #



Cloud Natural Language

Analyze text using ML to extract relevant entities, understand the overall sentiment, identify parts of speech and create dependency parse trees.

Bookmarked on #


A Basic Lack of Understanding

How does artificial intelligence actually work, and what are its limitations?

Bookmarked on #


Letting neural networks be weird

"Machine learning algorithms are not like other computer programs. In the usual sort of programming, a human programmer tells the computer exactly what to do. In machine learning, the human programmer merely gives the algorithm the problem to be solved, and through trial-and-error the algorithm has to figure out how to solve it. […] But it doesn’t always work well. Sometimes the programmer will think the algorithm is doing really well, only to look closer and discover it’s solved an entirely different problem from the one the programmer intended."

Bookmarked on #


pix2code: Generating Code from a Graphical User Interface Screenshot

"Transforming a graphical user interface screenshot created by a designer into computer code is a typical task conducted by a developer in order to build customized software, websites, and mobile applications. In this paper, we show that deep learning methods can be leveraged to train a model end-to-end to automatically generate code from a single input image with over 77% of accuracy for three different platforms (i.e. iOS, Android and web-based technologies)."

Bookmarked on #


Machine Learning for Kids

An educational tool for teaching kids about machine learning, by letting them train a computer to recognise text, pictures or numbers, and make things with it in Scratch.

Bookmarked on #


Preparing for Malicious Uses of AI

"We've co-authored a paper that forecasts how malicious actors could misuse AI technology, and potential ways we can prevent and mitigate these threats."

Bookmarked on #



Family fun with deepfakes. Or how I got my wife onto the Tonight Show

"The deepfakes app is a deep learning algorithm that learns how to reconstruct faces. Give it a bunch of pictures, let it run a few hours, and it spits out fuzzy copies of those images. Do note, it doesn’t create a copy. It learns what a face looks like, in different expressions, and is able to output that face solely based on that."

Bookmarked on #


Doxel - Artificial Intelligence for Construction Productivity - Doxel AI

Software that inspects quality and tracks progress so you can react in minutes, not months.

Bookmarked on #


The Stanford Question Answering Dataset

"Stanford Question Answering Dataset (SQuAD) is a new reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage. With 100,000+ question-answer pairs on 500+ articles, SQuAD is significantly larger than previous reading comprehension datasets."

Bookmarked on #


Turning Design Mockups Into Code With Deep Learning

"In this post, we’ll teach a neural network how to code a basic a HTML and CSS website based on a picture of a design mockup. Here's a quick overview of the process."

Bookmarked on #


Keras Documentation

"Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research."

Bookmarked on #


TensorFlow

An open-source software library for Machine Intelligence

Bookmarked on #


Caffe

Caffe is a deep learning framework made with expression, speed, and modularity in mind.

Bookmarked on #


Fabrik visual neural net builder

Collaboratively build, visualize, and design neural nets in browser.

Bookmarked on #


Every single Machine Learning course on the internet, ranked by your reviews

"For this guide, I spent a dozen hours trying to identify every online machine learning course offered as of May 2017, extracting key bits of information from their syllabi and reviews, and compiling their ratings. My end goal was to identify the three best courses available and present them to you, below."

Bookmarked on #


Feature Visualization

How neural networks build up their understanding of images

Bookmarked on #


Neural network image super-resolution and enhancement

Free online image upscale and JPEG artifact removal using netural networks. Image superresolution and image enhancement online.

Bookmarked on #




Caffe2

A New Lightweight, Modular, and Scalable Deep Learning Framework

Bookmarked on #


Fooling Neural Networks in the Physical World with 3D Adversarial Objects

We've developed an approach to generate 3D adversarial objects that reliably fool neural networks in the real world, no matter how the objects are looked at.

Bookmarked on #


prosthetic knowledge

Progressive Growing of GANs for Improved Quality,...

Bookmarked on #


The Juvet Agenda

Artificial intelligence? It’s complicated. It’s the here and now of hyper-efficient algorithms, but it’s also the heady possibility of sentient systems.

Bookmarked on #


Sketching Interfaces

Generating code from low fidelity wireframes.

Bookmarked on #


AI Experiments

A showcase for simple experiments that make it easier for anyone to start exploring machine learning, through pictures, drawings, language, music, and more.

Bookmarked on #


AI Security

A curated list of AI security resources

Bookmarked on #