Processing math: 100%
Table of Contents
1.
Machine Learning Primer -- Part III: Advanced Topics
2.
ML Trends / Scaling / Varia
3.
efficient learning
4.
performance
Machine Learning Primer -- Part III: Advanced Topics
Claudius Gros, WS 2024/25
Institut für theoretische Physik
Goethe-University Frankfurt a.M.
ML Trends / Scaling / Varia
efficient learning
[
Cornell
]
Blog:
towards data science
Efficient Inference in Deep Learning - Where is the Problem?
(2020, by Amnon Geifman)
Petaflops:
10
15
floating point operations per seconds
CPU:
∼
0.1
⋅
10
12
GPU:
∼
(
1
−
10
)
⋅
10
12
d
a
y
ˆ
=
86.4
⋅
10
3
s
e
c
Moore's law
: performance of hardware doubles every 1.8-2 years
ML requirements
: doubling every 3-4 months
performance
Blog:
Medium
Computational Complexity of Deep Learning: Solution Approaches
(2021, by Vijay S. Agneeswaran)
performance as a function of resources (time, data, complexity)
ImageNet-1k
complexity: # of model parameters
complexity barrier
old/new ML: hard/soft
slide 1/4
*
help?
contents?
Space, Right Arrow or swipe left to move to next slide, click help below for more details