Sale on canvas prints! Use code ABCXYZ at checkout for a special discount!

Previous PagePREV

|

11 of 33

|

NEXTNext Page
Deep Learning Framed Print featuring the digital art Drop#2 by Javier Ideami

Frame

Top Mat

Top Mat

Bottom Mat

Bottom Mat

Dimensions

Image:

14.00" x 8.00"

Mat Border:

2.00"

Frame Width:

0.88"

Overall:

19.50" x 13.50"

 

Share This Page

Drop#2 Framed Print

Javier Ideami

by Javier Ideami

$84.00

Product Details

Drop#2 framed print by Javier Ideami.   Bring your print to life with hundreds of different frame and mat combinations. Our framed prints are assembled, packaged, and shipped by our expert framing staff and delivered "ready to hang" with pre-attached hanging wire, mounting hooks, and nails.

Design Details

Loss Landscape created with data from the training process of a convolutional network. Convnet, imagenette dataset, sgd-adam, bs=16, bn, lr sched,... more

Ships Within

3 - 4 business days

Additional Products

Drop#2 Digital Art by Javier Ideami

Digital Art

Drop#2 Canvas Print

Canvas Print

Drop#2 Framed Print

Framed Print

Drop#2 Art Print

Art Print

Drop#2 Poster

Poster

Drop#2 Metal Print

Metal Print

Drop#2 Acrylic Print

Acrylic Print

Drop#2 Wood Print

Wood Print

Framed Print Tags

framed prints machine learning framed prints artificial intelligence framed prints

Digital Art Tags

digital art machine learning digital art artificial intelligence digital art

Comments (0)

There are no comments for Drop#2.   Click here to post the first comment.

Artist's Description

Loss Landscape created with data from the training process of a convolutional network. Convnet, imagenette dataset, sgd-adam, bs=16, bn, lr sched, train mod, 250k pts, 20p-interp, log scaled (orig loss nums) & vis-adapted.

This piece has been created through a multi day process composed of different stages that begin with the training of deep learning neural networks and proceeds through a number of phases until arriving to the final artwork.

When analyzing the loss landscape generated while increasing dropout, we see a noise layer taking over the landscape, a layer that is disruptive enough to help in preventing overfitting and the memorization of paths and routes across the landscape, and yet not disruptive enough to prevent convergence to a good minima (unless dropout is taken to extreme values).

Created by Javier Ideami.
For more about the Loss Landscape project visit https://losslandscape.com

About Javier Ideami

Javier Ideami

Explorer of A.I, AR, advanced visualizations & others, multidisciplinary engineer & creative director. As a multidisciplinary creative director, engineer, artist and entrepreneur, Javier has travelled the world leading projects, exhibiting his work and giving talks, from Silicon Valley to the jungles of Bali, from Stanford University, through the United Nations FAO HQ and the financial center of London, to the International Cultural Diplomacy Conference in Berlin and many others. In his latest works, Javier Ideami produces A.I artworks through a complex process that can last many days. The process begins with training a neural network and capturing relevant data. This multidimensional data is then transformed into a 3D piece which is...

 

$84.00

Previous Page Next Page