Hardware independent LLM inference engine from ZML.
@ylecun
-
Amiga 1000 powered early tensor engine Lush development
By
–
True story.
I used this particular Amiga 1000 to write SN (Léon had his own Amiga) using Emacs and gcc, and to write my PhD thesis with Emacs and LaTeX in 1987.
SN, later evolved into SN2 and SN3, and was open sourced under the name Lush in 2001.
SN3/Lush (tensor engine with Lisp -
Convolutional Neural Network Implementation on SN-1 Hardware 1988
By
–
That convolutional net was implemented in SN-1, which was initially developed on this Amiga (and Léon's).
Training runs were executed on a Sun 4 at Bell Labs in late 1988. -
SN-1 Software: Training First LeNets in Deep Learning
By
–
SN-1 is the software I used to implement and train the first LeNets.
-
LeNet Implementation History: SN-1 Development and Early Neural Networks
By
–
LeNet was implemented in late 1988 using SN-1 originally developed on this Amiga and on Léon's Amiga.
I finished SN during my postdoc at the University of Toronto, implemented shared weights and a graphic output.
Experiments were run on a Sun 4 at Bell Labs in late 1988. -
Optimal batch size equals one for machine learning
By
–
The optimal batch size is 1
(For suitable definitions of "optimal") -
Iterative Updates Reduce AI Model Hyperparameter Dependency
By
–
More updates = more feedback = less dependency on hyperparamaters
-
Compressibility and Model Representation in Real-World Sequences
By
–
And the notion of "compressibility" says nothing about the tiny subset of sequences that are compressible.
The fact that the real-world sequences we choose to model are easily "compressed" by models that are simple to represent in the same world sounds a bit like a convenient -
World Comprehensibility and Inductive Bias in Intelligence
By
–
wellll, that's just because all the problems we can think of are very special.
As Einstein famously said "the most incomprehensible thing about the world is that the world is comprehensible."
Not only that, the world is comprehensible by brains whose inductive bias allows them to -
Report Yann LeCun to Company AI Chief Officer
By
–
You are welcome to report to the Chief AI Officer of whatever company this Yan LeCunn dude works at.