The Merging between AI and Wireless Communication - Keynote at IEEE Globecom Workshop on WCDI, 2022
MLRG KTH
The Merging between AI and Wireless Communication - Keynote at IEEE Globecom Workshop on WCDI, 2022
35:27
Wireless for Machine Learning - Tutorial
MLRG KTH
Wireless for Machine Learning - Tutorial
3:40:31
Machine Learning in the Air by Deniz Gunduz
MLRG KTH
Machine Learning in the Air by Deniz Gunduz
1:38:44
Learning at the Wireless Edge by Vince Poor
MLRG KTH
Learning at the Wireless Edge by Vince Poor
57:37
Panel Discussion
MLRG KTH
Panel Discussion
1:05:52
Sindri Magnússon: On the convergence limited communication gradient methods
MLRG KTH
Sindri Magnússon: On the convergence limited communication gradient methods
1:09:39
Pascal Bianchi: A dynamical system viewpoint on stochastic approximation methods
MLRG KTH
Pascal Bianchi: A dynamical system viewpoint on stochastic approximation methods
1:24:38
Hadi Ghauch: Large-scale training for deep neural networks
MLRG KTH
Hadi Ghauch: Large-scale training for deep neural networks
1:01:07
Lecture 8 part 2: Deep Neural Networks
MLRG KTH
Lecture 8 part 2: Deep Neural Networks
46:02
Lecture 8 part 1: Deep Neural Networks
MLRG KTH
Lecture 8 part 1: Deep Neural Networks
49:00
Lecture 7 part 2: Communication efficiency (general graph)
MLRG KTH
Lecture 7 part 2: Communication efficiency (general graph)
41:42
Lecture 7 part 1: Communication efficiency (master-worker architecture)
MLRG KTH
Lecture 7 part 1: Communication efficiency (master-worker architecture)
47:18
Lecture 6 part 2: ADMM (hyperparameter optimization and applications)
MLRG KTH
Lecture 6 part 2: ADMM (hyperparameter optimization and applications)
37:39
Lecture 6 part 1: ADMM (basic definitions and properties)
MLRG KTH
Lecture 6 part 1: ADMM (basic definitions and properties)
41:29
Lecture 5 part 2: Distributed ML (general communication topology)
MLRG KTH
Lecture 5 part 2: Distributed ML (general communication topology)
43:00
Lecture 5 part 1: Distributed ML (star communication topology)
MLRG KTH
Lecture 5 part 1: Distributed ML (star communication topology)
44:07
Lecture 4 part 2: Centralized Nonconvex ML (generic solvers)
MLRG KTH
Lecture 4 part 2: Centralized Nonconvex ML (generic solvers)
45:54
Lecture 4 part 1: Centralized Nonconvex ML (basic definitions and special structures)
MLRG KTH
Lecture 4 part 1: Centralized Nonconvex ML (basic definitions and special structures)
46:35
Lecture 3 part 2: Centralized Convex ML (part 2: stochastic algorithms)
MLRG KTH
Lecture 3 part 2: Centralized Convex ML (part 2: stochastic algorithms)
47:32
Lecture 3 part 1: Centralized Convex ML (part 2: stochastic algorithms)
MLRG KTH
Lecture 3 part 1: Centralized Convex ML (part 2: stochastic algorithms)
41:56
Lecture 2 part 2: Centralized Convex ML (part 1: deterministic algorithms)
MLRG KTH
Lecture 2 part 2: Centralized Convex ML (part 1: deterministic algorithms)
33:21
Lecture 2 part 1: Centralized Convex ML (part 1: deterministic algorithms)
MLRG KTH
Lecture 2 part 1: Centralized Convex ML (part 1: deterministic algorithms)
1:00:09
Lecture 1 part 1: Introduction
MLRG KTH
Lecture 1 part 1: Introduction
44:18
Lecture 1 part 2: Introduction
MLRG KTH
Lecture 1 part 2: Introduction
40:04
Seminar 15: Regret analysis for sequential decision making (part 3)
MLRG KTH
Seminar 15: Regret analysis for sequential decision making (part 3)
1:13:50
Seminar 14: Regret analysis for sequential decision making and online learning, part 2
MLRG KTH
Seminar 14: Regret analysis for sequential decision making and online learning, part 2
1:39:52
Seminar 13: Regret analysis for sequential decision making and online , part 1learning
MLRG KTH
Seminar 13: Regret analysis for sequential decision making and online , part 1learning
53:48
Seminar 12: Alternating direction method of multipliers for large scale optimization
MLRG KTH
Seminar 12: Alternating direction method of multipliers for large scale optimization
46:53
Seminar 11: Stochastic gradient methods
MLRG KTH
Seminar 11: Stochastic gradient methods
1:40:41
Seminar 9: Coordinate descent optimization methods
MLRG KTH
Seminar 9: Coordinate descent optimization methods
41:44
Seminar 7: Stochastic approximation
MLRG KTH
Seminar 7: Stochastic approximation
56:27
Seminar 5: Energy propagation in deep convolution neural networks
MLRG KTH
Seminar 5: Energy propagation in deep convolution neural networks
58:10
Seminar 6: Deep scattering transforms
MLRG KTH
Seminar 6: Deep scattering transforms
1:13:35
Seminar 3: On the approximation capabilities of neural networks
MLRG KTH
Seminar 3: On the approximation capabilities of neural networks
1:06:09
Seminar 4: Learnability of fully-connected neural networks
MLRG KTH
Seminar 4: Learnability of fully-connected neural networks
1:32:50
Seminar 10: Fundamentals of deep neural networks
MLRG KTH
Seminar 10: Fundamentals of deep neural networks
48:55
Seminar 2: PAC learnability in finite and infinite hypothesis spaces
MLRG KTH
Seminar 2: PAC learnability in finite and infinite hypothesis spaces
1:22:11
Seminar 1: Overview of ML techniques
MLRG KTH
Seminar 1: Overview of ML techniques
55:03