Machine learning at scale
Subscribe
Sign in
Home
Archive
About
New
Top
Changes ahead for Machine Learning at scale!
You read the title, so… What’s changing? I will cut right to the chase: Lately, the act of writing posts felt more of a chore rather than a pleasure. I…
Sep 17
•
Ludovico Bessi
6
Share this post
Changes ahead for Machine Learning at scale!
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
#36 Transformers as.. Support Vector Machines?!
Table of contents Introduction. Transformers == SVM? Closing thoughts. Introduction I have recently came across a new paper with the eye-catching title…
Sep 3
•
Ludovico Bessi
Share this post
#36 Transformers as.. Support Vector Machines?!
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
August 2023
#35 Machine UN-learning
Table of contents Introduction. Machine UN-learning. Closing thoughts. Introduction Google has recently introduced the "Machine Unlearning Challenge". I…
Aug 27
•
Ludovico Bessi
Share this post
#35 Machine UN-learning
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
#34 Scalable Second-order Optimizer for Language Model Pre-training
Table of contents Introduction. Scalable Stochastic Second-order Optimizer for Language Model Pre-Training. Closing thoughts. Introduction I have…
Aug 20
•
Ludovico Bessi
Share this post
#34 Scalable Second-order Optimizer for Language Model Pre-training
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
#33 Why Data Science projects fail?
Table of contents Introduction. Why Data Science projects fail? Closing thoughts. Introduction I came across [1] which peaked my interest. Machine…
Aug 13
•
Ludovico Bessi
Share this post
#33 Why Data Science projects fail?
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
#32 LoRA: Low rank adaptation. Finetuning LLM faster!
Table of contents Introduction. LoRA: Low rank adaptation. Finetuning LLM faster. Closing thoughts. Introduction In today's article I am going to…
Aug 6
•
Ludovico Bessi
Share this post
#32 LoRA: Low rank adaptation. Finetuning LLM faster!
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
July 2023
#31 Mixture of Experts for inference speed-ups of large scale Machine Learning models.
Table of contents Introduction. Mixture of Experts (MoE) inference and training for at scale AI. Closing thoughts. Introduction. In today's article I am…
Jul 30
•
Ludovico Bessi
Share this post
#31 Mixture of Experts for inference speed-ups of large scale Machine Learning models.
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
#30 Pruning vs Quantization. Final showdown!
Table of contents Introduction. Pruning vs quantization. Which one is better? Closing thoughts. Introduction I know what you might be thinking. I have…
Jul 23
•
Ludovico Bessi
Share this post
#30 Pruning vs Quantization. Final showdown!
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
#29 Object detection: one stage vs two stage networks and evaluation.
Table of contents Introduction. One stage vs two stage. Evaluating object detection models. Closing thoughts. Introduction In today's article I am going…
Jul 16
•
Ludovico Bessi
Share this post
#29 Object detection: one stage vs two stage networks and evaluation.
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
#28 Evaluating Machine Learning ranking models offline and online
Table of contents Introduction. Offline ranking metrics. Closing thoughts. Introduction In today's article I am going to discuss how to evaluate ranking…
Jul 9
•
Ludovico Bessi
Share this post
#28 Evaluating Machine Learning ranking models offline and online
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
#27 Gensyn: Decentralised Compute for Machine Learning. The solutions. [Part 2]
Table of contents Introduction. How to design such a system? Closing thoughts. Introduction In the previous article, I described a protocol for…
Jul 2
•
Ludovico Bessi
Share this post
#27 Gensyn: Decentralised Compute for Machine Learning. The solutions. [Part 2]
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
June 2023
#26 Gensyn: Decentralised Compute for Machine Learning. An introduction. [Part 1]
Table of contents Introduction. Introducing Gensyn. Closing thoughts. Introduction Today's article is going to discuss an interesting Litepaper: Gensyn…
Jun 25
•
Ludovico Bessi
Share this post
#26 Gensyn: Decentralised Compute for Machine Learning. An introduction. [Part 1]
www.machinelearningatscale.com
Copy link
Facebook
Email
Notes
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts