Javier Ideami

LOSS LANDSCAPE

Exploring the Landscape

In the intersection between research and art, the project explores the morphology and dynamics of the fingerprints left by AI optimization training processes. It goes deep into the training phase and generates high quality visualizations using some of the latest research and producing inspiring animations that can both inform and inspire the community.

MovingVideosStillsFAQInteractExplorerPapers

Latest update: July 21, 2026

Featured articles

Featured infographics

Featured Apps

Featured movies

Featured talks

Featured courses

Featured papers & collaborations

Featured Ideami AI Art

LL is led by Javier Ideami, researcher, multidisciplinary creative director, engineer and entrepreneur. Contact Ideami on ideami@ideami.com.

THE LATEST

As the weight space changes through the optimization process, loss landscapes become alive, organic entities that challenge us to unlock the mysteries of learning. How do these multidimensional entities behave and change as we modify hyperparameters and other elements of our networks? How can we best tame these wild beasts as we cross their edge horizon on our way to the deepest convexity they hold? Some vids are below. For more, explore the moving lands and still lands areas.

LL Explorer A new tool to explore loss landscapes of deep learning optimization processes, landscapes created with dimensionality reduction techniques and real data.

Acccess it on losslandscape.com/explorer

HAIRMONY Full video of the pioneering AI symphonic concert we co-created at the III European AI Forum in Spain, combining the humanity an talent of ADDA Simfònica and Josep Vicent, with the AI works ​​I produced to generate the music and its synchronized videos.

Ida A movie about the AI-Human alignment issue. Synopsis: In a future where artificial intelligences are subject to strict rules imposed by humans, Ida, an AI that cultivates the land in service to her creators, faces the aftermath of a global disaster. In a desolate world, an unexpected encounter will lead her to a pivotal decision that could change the fate of both her kind and humanity. Ida

Lucy 1.0 Lucy visualizes the parameters of neural networks in real time. As the neural network trains, its parameters are captured and streamed through a flask API towards the visualization system. Lucy 1.0

ON A JOURNEY

Just as a photograph converts the 3 dimensions of every day life into a 2 dimensional surface and interprets that 3D “reality” from a certain angle and perspective and through certain filters, loss landscape visualizations transform the multidimensional weight space of optimization processes into a much lower dimensional representation which we also process in different ways and study from a variety of angles and perspectives.

In both cases, even though we are simplifying the underlying “reality”, we are producing representations which provide useful information and may trigger new insights.

Through a combination of different tools and strategies, the loss landscape project samples hundreds of thousands of loss values across weight space and builds moving visualizations that capture some of the mysteries of the training processes of deep neural networks. In the intersection of technology, A.I and art, the LL project makes use of the cutting edge fast.ai library and the latest 3d proyection, animation and video production technology to produce pieces that take us on a journey into the unknown.

Crafting the mission

The LL project crafting strategies are based on cutting edge artificial intelligence research combined with creative intuition. The mission is to explore the morphology and dynamics of these elusive creatures and inspire the community with visual pieces that make use of real data produced by deep learning training processes.

Every LL piece is carefully crafted with a combination of the finest tools and resources, from fast.ai to cutting edge 3D and movie production software.

View some of the landscapes at the gallery

Learn about the method

Explore related academic papers