Posts
1408
Following
142
Followers
868
I'm a bit of an eclectic mess ๐Ÿ™‚ I've been a programmer, journalist, editor, TV producer, and a few other things.

I'm currently working on my second novel which is complete, but is in the edit stage. I wrote my first novel over 20 years ago but then didn't write much till now.

I post about #Coding, #Flutter, #Writing, #Movies and #TV. I'll also talk about #Technology, #Gadgets, #MachineLearning, #DeepLearning and a few other things as the fancy strikes ...

Lived in: ๐Ÿ‡ฑ๐Ÿ‡ฐ๐Ÿ‡ธ๐Ÿ‡ฆ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡ณ๐Ÿ‡ฟ๐Ÿ‡ธ๐Ÿ‡ฌ๐Ÿ‡ฒ๐Ÿ‡พ๐Ÿ‡ฆ๐Ÿ‡ช๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ต๐Ÿ‡น๐Ÿ‡ถ๐Ÿ‡ฆ๐Ÿ‡จ๐Ÿ‡ฆ

Fahim Farook

And thatโ€™s the end of another day of paper reading โ€” some really interesting (to me at least) stuff today but only 7 papers in the cs.CV category (and one outside) boosted from a total of 97 papers on arXiv.org today โ€ฆ

#AI #CV #NewPapers #DeepLearning #MachineLearning
0
1
0

Fahim Farook

"Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis. (arXiv:2209.08891v2 [cs.CV] UPDATED)" โ€” An interesting look at how replacing Latin characters with non-Latin (visual) equivalents, generative models reflect cultural stereotypes and biases in their generated images.

Paper: http://arxiv.org/abs/2209.08891

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
Example of homoglyph manipulatiโ€ฆ
0
1
0

Fahim Farook

"Dark solitons in Bose-Einstein condensates: a dataset for many-body physics research. (arXiv:2205.09114v2 [cond-mat.quant-gas] UPDATED)" โ€” A dataset of over 1.6ร—10โด experimental images of Bose-Einstein condensates containing solitonic excitations to enable machine learning (ML) for many-body physics research.

Paper: http://arxiv.org/abs/2205.09114

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
(a)โ€“(c) Raw data from which datโ€ฆ
0
0
1

Fahim Farook

"IยฒSB: Image-to-Image Schrรถdinger Bridge. (arXiv:2302.05872v1 [cs.CV])" โ€” A new class of conditional diffusion models that directly learn the nonlinear diffusion processes between two given distributions.

Paper: http://arxiv.org/abs/2302.05872

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
Outputs of our proposed Image-tโ€ฆ
0
3
2

Fahim Farook

"Heckerthoughts" โ€” A manuscript going through the basic concepts central to AI and Machine Learning where the author claims that some concepts he included are missing from modern ML courses. Conversational style, anecdotal, and not too long at 54 pages. Worth reading โ€ฆ

Paper: https://arxiv.org/abs/2302.05449

#AI #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
The โ€œburstโ€ of emails that promโ€ฆ
0
4
1

Fahim Farook

"Stochastic Surprisal: An inferential measurement of Free Energy in Neural Networks. (arXiv:2302.05776v1 [cs.LG])" โ€” A framework that allows for action during inference in supervised neural networks.

Paper: http://arxiv.org/abs/2302.05776
Code: https://github.com/olivesgatech/Stochastic-Surprisal

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
Stochastic surprisal answers coโ€ฆ
0
1
1

Fahim Farook

"Adding Conditional Control to Text-to-Image Diffusion Models. (arXiv:2302.05543v1 [cs.CV])" โ€” A method to control pretrained large diffusion models to support additional input conditions which can be used to augment existing generative models such as StableDiffusion by enabling conditional inputs like edge maps, segmentation maps, keypoints, etc.

Paper: http://arxiv.org/abs/2302.05543
Code: https://github.com/lllyasviel/ControlNet

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
Control Stable Diffusion with Cโ€ฆ
0
2
0

Fahim Farook

"MaskSketch: Unpaired Structure-guided Masked Image Generation. (arXiv:2302.05496v1 [cs.CV])" โ€” An image generation method that uses a guiding sketch to generate realistic images that match the structure of the sketch.

Paper: http://arxiv.org/abs/2302.05496

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
Given an input sketch and its cโ€ฆ
0
1
0

Fahim Farook

"Element-Wise Attention Layers: an option for optimization. (arXiv:2302.05488v1 [cs.LG])" โ€” A new method of attention mechanism which uses matrices multiplications and has shown 92% accuracy and a 97% reduction in parameters for the Fashion MNIST dataset.

Paper: http://arxiv.org/abs/2302.05488

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too ๐Ÿ™‚>>
The outputs of the attention moโ€ฆ
0
1
0

Fahim Farook

A total of 97 papers in the cs.CV category on arXiv.org today โ€” 40 new, 57 updated.

That seems a little daunting today since thereโ€™s other stuff I want to work on too, but I guess weโ€™ll just have to see how many interesting papers there are out of the lot?

#AI #CV #NewPapers #DeepLearning #MachineLearning
0
0
0

Morning all,

I wish you all a happy Monday.

A shot of a beautiful little Robin for todays image, the local nature reserve has many of these at this time of year, and they are all fearless, happy to get really close.

1
1
0

in another entry for i give you this very nice mourning dove sitting on the edge of a platform bird feeder. all birds are good birds, even the ones that may normally get overlooked or are rather common where you are

3
2
0

New preprint "Opaque prior distributions in Bayesian latent variable models", where we describe issues with priors that are easy to overlook and that can lead to incorrect or irreproducible results. The paper is informed by mistakes that I've made over the years.

https://arxiv.org/abs/2301.08667

1
3
0

Noa Kallioinen gave a short tutorial on how to do prior and likelihood sensitivity analysis (prior sensitivity can be due to prior-likelihood conflict or due to a weak likelihood) with `priorsense` R package in Bayes@Lund and the 18min video is now available https://www.youtube.com/watch?v=TBXD3HjcIps&list=PLUEhQLNNQrgndd7_ZY-U5x9lYssl25jmd&index=13

0
2
0

Arcades never died. They just returned to the wild

0
1
0

Roxi Horror ๐Ÿ’€๐ŸŒธ

That feeling when he says you look angelic but you donโ€™t know if he means you look really pretty or if you have an abnormally high number of eyeballs.

3
3
0

๐•ฟ๐–—๐–Ž๐–‹๐–‘๐–Ž๐–“๐–Œ๐•ฟ๐–—๐–Š๐–Šโ“

Art Nouveau style spacesuit with helmet
Midjourney 4 AI Art

0
1
0

๐•ฟ๐–—๐–Ž๐–‹๐–‘๐–Ž๐–“๐–Œ๐•ฟ๐–—๐–Š๐–Šโ“

Colorful Baby Salamander
Midjourney 4 AI Art

0
1
0
Show older