Posts
1639
Following
139
Followers
885
I'm a bit of an eclectic mess 🙂 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: 🇱🇰🇸🇦🇺🇸🇳🇿🇸🇬🇲🇾🇦🇪🇫🇷🇪🇸🇵🇹🇶🇦🇨🇦

Fahim Farook

"Real-Time Evaluation in Online Continual Learning: A New Paradigm. (arXiv:2302.01047v1 [cs.LG])" — A practical real-time evaluation of continual learning, in which the stream does not wait for the model to complete training before revealing the next data for predictions.

Paper: http://arxiv.org/abs/2302.01047

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
OCL Real-Time Evaluation Exampl…
0
1
0

Fahim Farook

"Multimodal Chain-of-Thought Reasoning in Language Models. (arXiv:2302.00923v1 [cs.CL])" — A Multimodal Chain-of-Thought that incorporates vision features in a decoupled training framework which separates the rationale generation and answer inference into two stages and incorporates vision features in both stages.

Paper: http://arxiv.org/abs/2302.00923

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Example of the multimodal CoT t…
0
2
0

Fahim Farook

"Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment. (arXiv:2302.00902v1 [cs.LG])" — A modification of VQ-VAE that learns to align text-image data in an unsupervised manner by leveraging pretrained language models (e.g., BERT, RoBERTa).

Paper: http://arxiv.org/abs/2302.00902

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Language Quantization AutoEnco…
0
2
0

Fahim Farook

"Disentanglement of Latent Representations via Sparse Causal Interventions. (arXiv:2302.00869v1 [cs.LG])" — A new method for disentanglement inspired by causal dynamics that combines causality theory with vector-quantized variational autoencoders where the model considers the quantized vectors as causal variables and links them in a causal graph.

Paper: http://arxiv.org/abs/2302.00869

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Atomic interventions on one fac…
0
3
0

Fahim Farook

"SHINE: Deep Learning-Based Accessible Parking Management System. (arXiv:2302.00837v1 [cs.CV])" — A system which uses deep learning object detection algorithms to detect the vehicle, license plate, and disability badges and then authenticates the rights to use the accessible parking spaces by coordinating with a central server.

Paper: http://arxiv.org/abs/2302.00837

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
An overview of the methodology
0
1
0

Fahim Farook

A total of 72 papers in the cs.CV category on arXiv.org today — 56 new, 16 updated.

Let’s read some papers!

#AI #CV #NewPapers #DeepLearning #MachineLearning
0
0
0
Personal
Show content
@Miteroni Well, at least you know it’s not something to worry about, right? 🙂 That kind of worry is rather annoying because it sits at the back of your mind gnawing away … and comes back when you are just falling asleep or have a quiet moment. So probably a good thing you don’t have to worry.
1
0
1

CatGPT uncovered! Amongst his top sitting spots.

0
1
0

The next time you use any navigation device, software or Google Maps thank Dr. Gladys West. Her contributions to the mathematical modeling of the shape of Earth, and her work on the development of the satellite models that were eventually incorporated into  the Global Positioning System (GPS) technology.

1
7
0
@andrey I do hope people keep joining and Sigmoid was extremely useful when I joined in finding other people in #MachineLearning 🙂

Regarding people dropping out, is it possible that they are perhaps moving to their own instances or, as they get more used to the Fediverse, moving to other places which have the particular functionality they are looking for?

Speaking for me personally, I found that posting about #MachineLearning papers, I constantly kept hitting the 500 character limit and had to struggle sometimes to condense things down to 500 characters 😛

Plus, I had plans to doing serialised stories on here and 500 characters was just too limiting …

So I switched to my own Akkoma instance which gave me the ability to have much longer posts. Doing papers daily is much easier now since I don’t have to spend a lot of time trying to stick to the 500 character limit ….

So possibly there are others who are moving for similar (or other) reasons? I don’t know … Just suggesting a possibility.
1
0
2

Fahim Farook

On the Fediverse you definitely get more engagement, however, some of that engagement is rather weird 😛

Just over the last 24 hours, I’ve seen at least three such engagements where people make cryptic, drive-by-remarks which either misunderstand the original post, or is completely off the point.

Since I’ve had very little engagement with people I didn’t follow on Twitter, I don’t know if this is normal or not. But it seems a little weird to me …

The one personal engagement of the ones I mentioned above was my wife getting a reply about an art project she was doing. She was doing the art for something I was working on and she mentioned it was at my request. She also mentioned that she was using a particular type of brush. She gets a response saying that she shouldn’t be dictated to as to what type of brush she uses …

We were both mystified since she didn’t say she was using the brushes at my request, nor at anybody else’s. So why the comment? Just poor reading skills? Jumping to conculsions? Or just the need to insert yourself into other people’s lives right or wrong? 😛

I have no idea … (Of course, as a disclaimer, these interactions are the exception. Most interactions here on the Fediverse have been really great and I do like being here way more than Twitter …)
1
0
1

The feeling of being in a hollow tree is like being tucked up in a living bed

Willow on Streatham Common

0
1
0
@AlexKourvo To the original question, I don’t know if all men do it or not, but I certainly don’t 🙂 When I’m at home I generally wear a sarong and so don’t even have pockets. Plus, why bother with all that. But what I can tell you is that my house key (which is the only key I have) is in my “outside” pants pocket all the time because I don’t want to forget it when I go out 😛 Maybe that (or a similar reason) is why your Dad does it too?

@dipti My grandmother did it too 🙂 I always thought it was a power move because there were multiple families living in that house and nobody could take stuff out of the larder/pantry unless she opened it. But of course, each of those families had their own stores too … But she controlled the “big” store 😀
0
0
0
@BobStep Could be that it’s collecting/archiving your posts. I’ve heard of instances which have bots which follow you so that they can slurp up your timeline and archive it etc.

There was a brouhaha a while back about such an instance, and they had an account called “Everybody” which would follow you. I blocked that account. One of the few I’ve blocked on here …
0
0
1

are not fun. If anyone is looking for a in tech, ProductHunt has listed a few openings at various companies.

👉🏾 https://www.producthunt.com/jobs

Also Automattic is hiring as well.

👉🏾 https://automattic.com/work-with-us/

Yes, I am still upset with various companies laying off tens of thousands of workers & then doing stock buybacks worth billions of dollars! 😡

0
1
0

Guten Morgen

Am (und irgendwie auch ) gibt es ein Bild aus dem beschaulichen in der .

is a picturesque little town in which lies near an enchanted forest. It is truly magical 🧙‍♂️and a heaven for fans!

2
3
1
Show older