en
0.25
0.5
0.75
1.25
1.5
1.75
2
Lecture 15: Data Modelling With Neural Networks (I): Feedforward Networks: The Capacity Of A Single Neuron, Learning As Inference
Published on Nov 05, 201215755 Views
Related categories
Chapter list
Neural Networks (1)00:00
Course Outline00:04
Reading00:18
Brains (1)00:28
How To Make Content-Addressable Memory?00:59
Content-Addressable Memory (1)01:20
Content-Addressable Memory (2)02:42
Content-Addressable Memory (3)03:24
Content-Addressable Memory (4)03:31
Content-Addressable Memory (5)03:35
Brains (2)04:04
Difference Between A Pigeon And Supercomputer (1)05:50
Difference Between A Pigeon And Supercomputer (2)06:20
Difference Between A Pigeon And Supercomputer (3)07:37
Difference Between A Pigeon And Supercomputer (4)07:45
Difference Between A Pigeon And Supercomputer (5)09:18
Difference Between A Pigeon And Supercomputer (6)10:46
Difference Between A Pigeon And Supercomputer (7)11:48
Difference Between A Pigeon And Supercomputer (8)13:41
Parallel Distributed Processing (1)15:29
Parallel Distributed Processing (2)15:36
Parallel Distributed Processing (3)16:14
Parallel Distributed Processing (4)18:08
Parallel Distributed Processing (5)19:19
Parallel Distributed Processing (6)19:33
Variational Free Energy, Spin System (1)21:06
Variational Free Energy, Spin System (2)21:55
Classification (1)22:03
Classification (2)22:21
Single Neuron As Binary Classifier (1)23:10
Learning For A Single Neuron (1)23:21
Learning For A Single Neuron (2)23:51
What Happens If The Weights Are Doubled? (1)25:39
What Happens If The Weights Are Doubled? (2)28:00
What Happens If The Weights Are Doubled? (3)29:02
Learning (1)29:33
Learning (2)30:03
Learning (3)30:18
Learning (4)30:48
Learning (5)31:15
Learning (6)31:44
Learning (7)31:53
Learning (8)32:07
Single Neuron Example Results (1)33:14
Gradient Descent (1)34:27
Gradient Descent (2)34:47
Gradient Descent (3)35:30
Gradient Descent (4)36:32
Gradient Descent (5)36:59
Gradient Descent (6)37:12
Gradient Descent (7)37:15
Gradient Descent (8)37:21
Learning With Regularization (1)38:35
Learning With Regularization (2)39:39
Learning With Regularization (3)39:58
Learning With Regularization (4)40:45
Learning With Regularization (5)40:50
Learning With Regularization (6)41:05
Learning With Regularization (7)41:14
Single Neuron For Digit Classification (1)42:13
Single Neuron For Digit Classification (2)43:04
Capacity Of A Neuron (1)43:33
Multi-layer Network For Regression (1)46:54
Multi-layer Network For Regression (2)47:33
Multi-layer Network For Regression (3)48:43
Multi-layer Network For Regression (4)49:48
Multi-layer Network For Regression (5)51:57
Steepest Descents (1)53:13
Steepest Descents (2)53:55
Steepest Descents (3)54:59
Regularizer (1)55:15
Regularizer (2)56:19
Regularizer (3)58:15
Steepest Descents (4)58:38
Steepest Descents (5)58:58
Steepest Descents (6)59:07
Single Neuron Pigeon Replacement Results (1)59:46
Single Neuron Pigeon Replacement Results (2)01:00:13
Optimized Single Neuron Pigeon Replacement Results (1)01:01:00
Learning As Inference (1)01:01:54
Learning As Inference (2)01:02:26
Learning As Inference (3)01:02:46
Learning As Inference (4)01:04:17
Prediction (1)01:05:03
Prediction (2)01:05:58
Langevin Method (1)01:07:27
Langevin Method (2)01:08:27
Langevin Method (3)01:08:40
Langevin Method (4)01:09:09
Langevin Method (5)01:09:22
Langevin Method (6)01:09:45
Langevin Method (7)01:10:11
Langevin Method (8)01:10:45
Langevin Method (9)01:10:55
Langevin Method (10)01:11:33
Langevin Method (11)01:12:18
Langevin Method (12)01:12:49
Laplace Approximation (1)01:13:17
Langevin Method (13)01:14:09
Langevin Method (14)01:14:20
Laplace Approximation (2)01:14:51
Laplace Approximation (3)01:15:35
Laplace Approximation (4)01:15:36
Laplace Approximation (5)01:15:40
Feedforward Neural Networks (1)01:16:03
Multi-layer Network For Regression (6)01:16:05
Applications (1)01:16:08
Langevin Method (15)01:16:57
Langevin Method (16)01:17:06
Langevin Method (17)01:17:28
Langevin Method (18)01:18:23
Multi-layer Network For Regression (7)01:18:30
Applications (2)01:18:41
Applications (3)01:19:08
Applications (4)01:19:49
Applications (5)01:20:32
Applications (6)01:22:13
Applications (7)01:22:56
Brains (3)01:23:46
Brains (4)01:24:20
Content-Addressable Memory (6)01:24:41
Content-Addressable Memory (7)01:24:53