Artificial intelligence has recently spiked a significant popular interest especially due to easily accessible language models and image processing. 
In the audio realm, both sound processing as well as neural audio synthesis are becoming an integral part of the creative process and production chain and force us to reconsider established formations. 

Spoor has been written in collaboration with an artificial representation of myself in the form of various RAVE models that have been trained on different parts of my body of work. 
I consider these models instruments. I want to learn playing these instruments but I also want these models to hallucinate for me to observe, learn and react. 

RAVE is "A variational autoencoder for fast and high-quality neural audio synthesis” created by Antoine Caillon and Philippe Esling at Artificial Creative Intelligence and Data Science (ACIDS) w/ IRCAM, Paris. 

Paper: arxiv.org/abs/2111.05011 
Source: github.com/acids-ircam/RAVE

Spoor

Architects

Spoor Loop

Spoor Widen has been written in collaboration with an artificial representation of the artist in the form of a RAVE model trained on parts of their body of work.

Recorded in October 2023

RAVE is "A variational autoencoder for fast and high-quality neural audio synthesis” created by Antoine Caillon and Philippe Esling at Artificial Creative Intelligence and Data Science (ACIDS) w/ IRCAM, Paris. 

Paper: arxiv.org/abs/2111.05011 
Source: github.com/acids-ircam/RAVE

Spoor Widen

Wap Ai

One of the shorter improvs of the model. Still beautiful.

4 - Shour Improvisation with Deep Learning

5 - Shour Improvisation with Deep Learning

Saatgut Proxy is an experimental generative setup that creates both randomized and repeatable pathways through the latent space of two neural audio/ AI model architectures (RAVE, vschaos2) which have been trained on parts of my own body of work. 

RAVE is "A variational autoencoder for fast and high-quality neural audio synthesis” created by Antoine Caillon and Philippe Esling. https://arxiv.org/abs/2111.05011

vschaos2 "is a vintage-flavoured neural audio synthesis package. It is based on unsupervised / (semi-)supervised training of spectral information using variational auto-encoders“ created by Axel Chemla Romeu Santos. https://hal.science/tel-03543235

Source:
https://github.com/acids-ircam/RAVE 
https://github.com/acids-ircam/vschaos2
https://github.com/acids-ircam/nn_tilde

Saatgut Proxy

Tritt Nochmal Zu

Nausea Seeder

Rauten

Proxy Proxy

Explore the groundbreaking Mamba model, a potential game-changer in AI that promises to outpace the traditional Transformer architecture with its efficient, linear-time sequence modeling.

Additional materials: www.superdatascience.com/758

Interested in sponsoring a SuperDataScience Podcast episode? Visit passionfroot.me/superdatascience for sponsorship information.

The Super Data Science Podcast: Machine Learning | AI | Success

758: The Mamba Architecture: Superior to Transformers in LLMs

In this Tech Barometer podcast segment, Greg Diamos tells how an early passion for computing led him to a pioneering role Baidu’s Silicon Valley AI lab, where he discovered ways to scale deep learning systems, and went on to co-found MLCommons and AI company Lamini.

Find more enterprise cloud news, features stories and profiles at The Forecast:
http://www.theforecastbynutanix.com/

Transcript:
https://media24.connectedsocialmedia.com/nutanix/03/20669/Greg_Diamos_AI_ML_software_pioneer.pdf

Artificial Intelligence

Greg Diamos AI and ML software pioneer

Generative AI in medicine takes center stage as Prof. Zachary Lipton, Chief Scientific Officer at Abridge, joins host Jon Krohn to discuss the significant advancements in AI that are reshaping healthcare.

This episode is brought to you by the DataConnect Conference (https://www.dataconnectconf.com/dccwest/conference), and by Data Universe, the out-of-this-world data conference (https://datauniverse2024.com). Interested in sponsoring a SuperDataScience Podcast episode? Visit passionfroot.me/superdatascience for sponsorship information.

In this episode you will learn:
• The inspiration for Zack to get started in ML and healthcare [03:56]
• The hardware required to use Abridge [12:29]
• The key data science projects at Abridge right now [35:05]
• Abridge's tech stack [59:54]
• How Abridge ensures reliability in a high-stakes setting like healthcare [1:07:29]
• How Zack’s academic research cross-pollinates with his commercial ML projects [1:21:05]
• How Zack’s jazz background molded his entrepreneur and data science journey [1:30:32]

Additional materials: www.superdatascience.com/769

769: Generative AI for Medicine, with Prof. Zack Lipton

The Supersized Science podcast features research and discoveries nationwide enabled by advanced computing technology and expertise at the Texas Advanced Computing Center of the University of Texas at Austin. 

The key to understanding proteins — such as those that govern cancer, COVID-19, and other diseases — is quite simple - for scientists, anyway.  Identify their chemical structure and find which other proteins can bind to them. But there’s a catch in that the search space for proteins is enormous. 

For instance, a typical protein studied is made of 65 amino acids, and with 20 different amino acid choices at each  binding position, there are 65 to the 20th power binding combinations, a number bigger than the estimated number of atoms there are in the universe.

Joining host and TACC science writer Jorge Salazar on the podcast are Brian Coventry, a research scientist with the Institute for Protein Design, University of Washington and The Howard Hughes Medical Institute; and Nathaniel Bennett, a post-doctoral scholar at the Institute for Protein Design.

Coventry and Bennett co-authored a study published May 2023 in the journal Nature Communications. 

In it their team used deep learning methods on TACC’s Frontera supercomputer to augment existing energy-based physical models in ‘do novo’ or from-scratch computational protein design, resulting in a 10-fold increase in success rates verified in the lab for binding a designed protein with its target protein.

Music Credit: Raro Bueno, Chuzausen freemusicarchive.org/music/Chuzausen/

Story link: https://www.tacc.utexas.edu/news/latest-news/2023/08/03/deep-learning-for-new-protein-design/

Deep Learning for New Protein Design

Dr. Barrett Thomas, an award-winning Research Professor at the University of Iowa, explores the intricacies of Markov decision processes and their connection to Deep Reinforcement Learning. Discover how these concepts are applied in operations research to enhance business efficiency and drive innovations in same-day delivery and autonomous transportation systems.

This episode is brought to you by Ready Tensor, where innovation meets reproducibility (https://www.readytensor.ai/). Interested in sponsoring a SuperDataScience Podcast episode? Visit passionfroot.me/superdatascience for sponsorship information.

In this episode you will learn:
• Barrett's start in operations logistics [02:27]
• Concorde Solver and the traveling salesperson problem [09:59]
• Cross-function approximation explained [19:13]
• How Markov decision processes relate to deep reinforcement learning [26:08]
• Understanding policy in decision-making contexts [33:40]
• Revolutionizing supply chains and transportation with aerial drones [46:47]
• Barrett’s career evolution: past changes and future prospects [52:19]

Additional materials: www.superdatascience.com/773

773: Deep Reinforcement Learning for Maximizing Profits, with Prof. Barrett Thomas

Epoch 062-2, Excerpt from
On a winter's night a traveller [The Deeply Learned Clavier] for solo piano
Ariel Mo, Piano
Brown Hall, New England Conservatory, Boston MA
April 2024

Program notes:
As evident from my website, I have recently replaced numerous pictures on the homepage with artificially synthesized images using a Deep Learning application. Nearly half of the images featured here have been generated by the “discord.” The rapid evolution of AI and Deep Learning algorithms is truly remarkable, and artists in the 21st century might find themselves in competition with AI-driven creations. Rather than compete with the technology, I find pleasure in embracing machines as collaborative creative partners.

In 2022, I embarked on a new phase of my research on Computer Music, in the field of Artificial Intelligence. To delve into this field, I studied MIT OCW’s Deep Learning course—a decision mirroring my choice back in 2010 when I studied differential equations, a significant contribution to my DMA research on virtual bells. For this, I began studying Python programming languages and exploring codes on the Google Colab platform. For over two months, I played with neural network codes, allowing the computer to learn circa 110 piano compositions written by Mozart. Following each learning process, which lasted between one and six hours (approximately 20 to 200 epochs—deep learning sequences), the computer generated fresh piano compositions within its comprehension of Mozart's musical context. Essentially, the computer composed pastiche pieces reminiscent of Mozart's style or aimed to counterfeit Mozart's works at its best.

Due to the limitations of my access to the Google Colab platform and the constraints of session timeouts, I was constrained to a maximum of six hours for each deep-learning process, despite the fact that these processes typically demand significantly longer durations, often ranging from several days to weeks and months. Additionally, the available volume of model data-works proved insufficient for generating authentic Mozart-esque piano work, e.g., having Alberti basslines or crisp and concise phrase models which we can easily find in his oeuvre. Nonetheless, the outputs/works compiled by the computer implied various intriguing features that we can often find in the tonal music repertoire, including the presence of ambiguous tonalities that bridged different keys and modal mixture, diatonic scales and modes, repetitions, various patterns of chords and arpeggios, oftentimes realized in awkward, crude and rudimentary, or even anti-contrapuntal, artificial(of course) and mechanistic ways, in distorted and grotesque shapes.

For about a month I listened to these outputs, and began tracing the trajectories of the computer’s unfulfilled thoughts. I was almost an archeologist who discovered a pile of unfinished, improvisatory, spurious sketches written by an unknown composer. During the discovery process, I tried to reveal the computer’s intentions, develop his/her/their imagination, and transform and elevate it into my own artwork.

It is commissioned by and dedicated with admiration and gratitude to Ariel Mo, who beautifully world-premiered my Le Tombeau de Harvey in January 2022.

Excerpt from On a winter's night a traveller for solo piano: Epoch 062-2, tempo giusto

Misterioso, Excerpt from
On a winter's night a traveller [The Deeply Learned Clavier] for solo piano
Ariel Mo, Piano
Brown Hall, New England Conservatory, Boston MA
April 2024

Program notes:
As evident from my website, I have recently replaced numerous pictures on the homepage with artificially synthesized images using a Deep Learning application. Nearly half of the images featured here have been generated by the “discord.” The rapid evolution of AI and Deep Learning algorithms is truly remarkable, and artists in the 21st century might find themselves in competition with AI-driven creations. Rather than compete with the technology, I find pleasure in embracing machines as collaborative creative partners.

In 2022, I embarked on a new phase of my research on Computer Music, in the field of Artificial Intelligence. To delve into this field, I studied MIT OCW’s Deep Learning course—a decision mirroring my choice back in 2010 when I studied differential equations, a significant contribution to my DMA research on virtual bells. For this, I began studying Python programming languages and exploring codes on the Google Colab platform. For over two months, I played with neural network codes, allowing the computer to learn circa 110 piano compositions written by Mozart. Following each learning process, which lasted between one and six hours (approximately 20 to 200 epochs—deep learning sequences), the computer generated fresh piano compositions within its comprehension of Mozart's musical context. Essentially, the computer composed pastiche pieces reminiscent of Mozart's style or aimed to counterfeit Mozart's works at its best.

Due to the limitations of my access to the Google Colab platform and the constraints of session timeouts, I was constrained to a maximum of six hours for each deep-learning process, despite the fact that these processes typically demand significantly longer durations, often ranging from several days to weeks and months. Additionally, the available volume of model data-works proved insufficient for generating authentic Mozart-esque piano work, e.g., having Alberti basslines or crisp and concise phrase models which we can easily find in his oeuvre. Nonetheless, the outputs/works compiled by the computer implied various intriguing features that we can often find in the tonal music repertoire, including the presence of ambiguous tonalities that bridged different keys and modal mixture, diatonic scales and modes, repetitions, various patterns of chords and arpeggios, oftentimes realized in awkward, crude and rudimentary, or even anti-contrapuntal, artificial(of course) and mechanistic ways, in distorted and grotesque shapes.

For about a month I listened to these outputs, and began tracing the trajectories of the computer’s unfulfilled thoughts. I was almost an archeologist who discovered a pile of unfinished, improvisatory, spurious sketches written by an unknown composer. During the discovery process, I tried to reveal the computer’s intentions, develop his/her/their imagination, and transform and elevate it into my own artwork.

It is commissioned by and dedicated with admiration and gratitude to Ariel Mo, who beautifully world-premiered my Le Tombeau de Harvey in January 2022.

Excerpt from On a winter's night a traveller for solo piano: Misterioso

On a winter's night a traveller [The Deeply Learned Clavier] (2022-23, rev. 2024) for solo piano
Ariel Mo, Piano
Brown Hall, New England Conservatory, Boston MA
April 2024
ca. 33 min.

Program notes:
As evident from my website, I have recently replaced numerous pictures on the homepage with artificially synthesized images using a Deep Learning application. Nearly half of the images featured here have been generated by the “discord.” The rapid evolution of AI and Deep Learning algorithms is truly remarkable, and artists in the 21st century might find themselves in competition with AI-driven creations. Rather than compete with the technology, I find pleasure in embracing machines as collaborative creative partners.

In 2022, I embarked on a new phase of my research on Computer Music, in the field of Artificial Intelligence. To delve into this field, I studied MIT OCW’s Deep Learning course—a decision mirroring my choice back in 2010 when I studied differential equations, a significant contribution to my DMA research on virtual bells. For this, I began studying Python programming languages and exploring codes on the Google Colab platform. For over two months, I played with neural network codes, allowing the computer to learn circa 110 piano compositions written by Mozart. Following each learning process, which lasted between one and six hours (approximately 20 to 200 epochs—deep learning sequences), the computer generated fresh piano compositions within its comprehension of Mozart's musical context. Essentially, the computer composed pastiche pieces reminiscent of Mozart's style or aimed to counterfeit Mozart's works at its best.

Due to the limitations of my access to the Google Colab platform and the constraints of session timeouts, I was constrained to a maximum of six hours for each deep-learning process, despite the fact that these processes typically demand significantly longer durations, often ranging from several days to weeks and months. Additionally, the available volume of model data-works proved insufficient for generating authentic Mozart-esque piano work, e.g., having Alberti basslines or crisp and concise phrase models which we can easily find in his oeuvre. Nonetheless, the outputs/works compiled by the computer implied various intriguing features that we can often find in the tonal music repertoire, including the presence of ambiguous tonalities that bridged different keys and modal mixture, diatonic scales and modes, repetitions, various patterns of chords and arpeggios, oftentimes realized in awkward, crude and rudimentary, or even anti-contrapuntal, artificial(of course) and mechanistic ways, in distorted and grotesque shapes.

For about a month I listened to these outputs, and began tracing the trajectories of the computer’s unfulfilled thoughts. I was almost an archeologist who discovered a pile of unfinished, improvisatory, spurious sketches written by an unknown composer. During the discovery process, I tried to reveal the computer’s intentions, develop his/her/their imagination, and transform and elevate it into my own artwork.

It is commissioned by and dedicated with admiration and gratitude to Ariel Mo, who beautifully world-premiered my Le Tombeau de Harvey in January 2022.

On a winter’s night a traveller [the Deeply Learned Clavier] for solo piano

The latest machine learning, A.I., and data career topics from across both academia and industry are brought to you by host Dr. Jon Krohn on the Super Data Science Podcast.

As the quantity of data on our planet doubles every couple of years and with this trend set to continue for decades to come, there's an unprecedented opportunity for you to make a meaningful impact in your lifetime. In conversation with the biggest names in the data science industry, Jon cuts through hype to fuel that professional impact.

Whether you're curious about getting started in a data career or you're a deep technical expert, whether you'd like to understand what A.I. is or you'd like to integrate more data-driven processes into your business, we have inspiring guests and lighthearted conversation for you to enjoy.

We cover tools, techniques, and implementation tricks across data collection, databases, analytics, predictive modeling, visualization, software engineering, real-world applications, commercialization, and entrepreneurship − everything you need to crush it with data science.

I try to write music that is oriented around acoustical phenomena and virtuosic classical performance practice. Please visit my website for more details.

Explore the cutting edge of enterprise cloud computing. Tech Barometer is the Podcast affiliate of The Forecast by Nutanix, which covers people and tech trends driving digital transformation. Business Ieaders, engineers and industry experts share insights and anecdotes about the quest to modernize IT.

Sound artist, audio programmer/ producer and DJ based in Berlin, Germany. AI + Neural Audio Synthesis + Generative Music ///// AKA Anthone. 1/2 of Bokeh (w/ Katsunori Sawa). Label = The Weevil Neighbourhood @weevilorchestra

The Supersized Science podcast highlights research and discoveries nationwide enabled by advanced computing technology and expertise at the Texas Advanced Computing Center of the University of Texas at Austin. TACC science writer Jorge Salazar hosts Supersized Science.

Supersized Science is part of the Texas Podcast Network, brought to you by The University of Texas at Austin. Podcasts are produced by faculty members and staffers at UT Austin who work with University Communications to craft content that adheres to journalistic best practices. The University of Texas at Austin offers these podcasts at no charge. Podcasts appearing on the network and this webpage represent the views of the hosts, not of The University of Texas at Austin.

New tracks tagged #deep learning