Posts tagged generative

XXXX Swatchbook shows the range of colours that can be achieved in handmade printing technique. But it also twists the idea of…

Evelin Kasikov, book design, stitching, book binding, generative, 2016

XXXX Swatchbook shows the range of colours that can be achieved in handmade printing technique. But it also twists the idea of print by turning quick reproduction process into slow handmade process. It’s a book about a process, and with no less than six years in the making, the book itself is a process. It’s a catalogue of colour, a unique art book and an object of book art. The book documents 400 hand-stitched colour swatches in CMYK embroidery. The line screen in my book is incredibly low and ranges between 4 to 7 lines per inch (as opposed to 300 lpi in standard printing).

The book is made of

4 colours
16 elements
400 colour combinations
219.647 stitches

Better Language Models and Their Implications

gpt2, ML, AI, text, text-generation, generative, OpenAI, 2019

GPT-2 displays a broad set of capabilities, including the ability to generate conditional synthetic text samples of unprecedented quality, where we prime the model with an input and have it generate a lengthy continuation. In addition, GPT-2 outperforms other language models trained on specific domains (like Wikipedia, news, or books) without needing to use these domain-specific training datasets. On language tasks like question answering, reading comprehension, summarization, and translation, GPT-2 begins to learn these tasks from the raw text, using no task-specific training data. While scores on these downstream tasks are far from state-of-the-art, they suggest that the tasks can benefit from unsupervised techniques, given sufficient (unlabeled) data and compute.

via https://blog.openai.com/better-language-models/

Synthetic Nature Part 1 by Andy Thomas  “Inspired by Australian flora and fauna. It is nature digitized. Sounds recorded in…

animation, Andy Thomas, synthetic nature, generative, 2016

video link

Synthetic Nature Part 1 by Andy Thomas 

“Inspired by Australian flora and fauna. It is nature digitized. Sounds recorded in nature have been run through computers and electronically manipulated. Computer generated 3D imagery swirls and contorts to the sounds creating semi-abstract interpretations of native plants.”

Deep Learning Techniques for Music Generation

arxiv, music, sound, generative, machine-learning, deep-learning

This book is a survey and an analysis of different ways of using deep learning (deep artificial neural networks) to generate musical content. At first, we propose a methodology based on four dimensions for our analysis: - objective - What musical content is to be generated? (e.g., melody, accompaniment…); - representation - What are the information formats used for the corpus and for the expected generated output? (e.g., MIDI, piano roll, text…); - architecture - What type of deep neural network is to be used? (e.g., recurrent network, autoencoder, generative adversarial networks…); - strategy - How to model and control the process of generation (e.g., direct feedforward, sampling, unit selection…). For each dimension, we conduct a comparative analysis of various models and techniques. For the strategy dimension, we propose some tentative typology of possible approaches and mechanisms. This classification is bottom-up, based on the analysis of many existing deep-learning based systems for music generation, which are described in this book

via https://arxiv.org/abs/1709.01620

WaveNet: A Generative Model for Raw Audio

audio, music, speech, synthesis, rnn, cnn, deepmind, generative, wavenets

This post presents WaveNet, a deep generative model of raw audio waveforms. We show that WaveNets are able to generate speech which mimics any human voice and which sounds more natural than the best existing Text-to-Speech systems, reducing the gap with human performance by over 50%. We also demonstrate that the same network can be used to synthesize other audio signals such as music, and present some striking samples of automatically generated piano pieces.

via https://deepmind.com/blog/wavenet-generative-model-raw-audio/

Paul Prudence interviews Mitchell Whitelaw

art, generative, futurism, utopianism, dystopianism, interview, paul prudence, mitchell whitelaw

It might be argued that some of the main themes infused in generative art are those to do with a kind of techno-utopianism and futurism. Have you come across any generative artworks that deal with dystopian themes or have a sense of anachronism about them? More importantly are the technologies and software used in creating these artworks inherently defining their aesthetics?

http://teemingvoid.blogspot.com.au/2012/01/interview-with-paul-prudence-for-neural.html