Sign inSign up
System Identification Using Machine Learning Methods thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

System Identification Using Machine Learning Methods

Published on Dec 03, 20124883 Views

Felix A. Wichmann

Understanding perception and the underlying cognitive processes on a behavioral level requires a solution to the feature identification problem: Which are the features on which sensory systems base th

BBCI Summer School

Related categories

Machine LearningNeuroscienceNeurotechnology

Chapter list

bbci2012_wichmann_system_identification_01_Page_00100:00
Former lab @ TU Berlin (1)01:27
Former lab @ TU Berlin (2)02:07
Image 103:44
Image 203:44
Image 303:45
Image 403:45
Image 503:45
Image 603:46
Image 703:46
Image 803:47
Image 903:47
Image 1003:48
How many animals?03:48
Animal detection in natural scenes: Critical features revisited06:08
Critical Features: System Identification (1)06:52
Critical Features: System Identification (2)07:25
Critical Features: System Identification (3)07:31
Critical Features: System Identification (4)07:53
Critical Features: System Identification (5)09:00
Critical Features: System Identification (6)09:28
Critical Features: System Identification (7)09:57
What is Machine Learning? (1)10:17
What is Machine Learning? (2)10:27
What is Machine Learning? (3)11:32
What is Machine Learning? (4)11:58
What is Machine Learning? (5)12:00
112:02
Gender Discrimination Task (1)12:49
Gender Discrimination Task (2)12:52
Gender Discrimination Task (3)12:53
Gender Discrimination Task (4)12:56
Gender Discrimination Task (5)12:58
Gender Discrimination Task (6)12:59
Gender Discrimination Task (7)13:01
Gender Discrimination Task (8)13:03
Gender Discrimination Task (9)13:06
Gender Discrimination Task (10)13:07
Gender Discrimination Task (11)13:09
Gender Discrimination Task (12)13:12
Gender Discrimination Task (13)13:12
Gender Discrimination Task (14)13:15
Gender Discrimination Task (15)13:30
Gender Discrimination Task (16)13:32
Gender Categorization of Human Faces (1)14:59
Gender Categorization of Human Faces (2)15:18
Gender Categorization of Human Faces (3)15:34
Gender Categorization of Human Faces (4)16:06
Linear Decision Rules (1)16:18
Linear Decision Rules (2)16:22
Linear Decision Rules (3)18:32
Linear Decision Rules (4)18:50
Linear Decision Rules (5)19:18
Linear Decision Rules (6)20:03
Linear Decision Rules (7)20:14
Linear Decision Rules (8)20:26
Psychometric Function along Logisitc Regression-ω 20:43
Psychometric Function along Prototype-ω22:27
Summary Statistics across Observers (1)23:29
Summary Statistics across Observers (2)24:17
How Good is the Prediction?25:32
Predictability and Reaction Times28:24
The Decision Images ω31:11
Evaluating Decision Images with Optimized Stimuli (1)33:09
Evaluating Decision Images with Optimized Stimuli (2)34:23
Evaluating Decision Images with Optimized Stimuli (3)34:41
Evaluating Decision Images with Optimized Stimuli (4)34:44
Evaluating Decision Images with Optimized Stimuli (5)34:55
Evaluating Decision Images with Optimized Stimuli (6)35:13
Interim Conclusions (1a)36:38
Interim Conclusions (1b)38:05
Interim Conclusions (1c)38:14
Interim Conclusions (1d)38:36
Interim Conclusions (1e)38:45
238:55
Scientific Question (1)39:17
Scientific Question (2)40:13
Previous Work (1)41:12
Previous Work (2)42:26
Previous Work (3)43:56
Saliency Maps45:01
Machine Learning Approach (1)45:47
Machine Learning Approach (2)45:53
Machine Learning Approach (3)46:20
Machine Learning Approach (4)46:32
Machine Learning Approach (5)47:01
Machine Learning Approach (6)47:08
Data Representation47:13
Background Examples48:53
Machine Learning Method (1a)50:04
Machine Learning Method (1b)50:06
Machine Learning Method (1c)50:09
Machine Learning Method (1d)50:21
Machine Learning Method (2a)50:31
Machine Learning Method (2b)50:32
Machine Learning Method (2c)50:41
Machine Learning Method (2d)50:43
Radial-Basis-Function Support Vector Machine (RBF-SVM)51:35
RBF-SVM after Optimization (“Learning”)52:06
Randomly Selected vs. Fixated Image Patches56:54
Randomly Selected vs. Fixated Patches: PCA Basis57:04
Randomly Selected vs. Fixated Patches: ICA Basis57:07
(a)57:09
(b)59:22
(c)01:01:20
(c1)01:01:40
(d)01:03:04
Non-linear Decision-Image Network for Visual Saliency01:03:26
Critical Controls (1)01:04:46
Critical Controls (2)01:04:48
Critical Controls (3)01:05:39
Critical Controls (4)01:05:42
bbcCritical Controls (5)01:05:49
Critical Controls (6)01:05:53
Occam’s Razor?01:06:40
Interim Conclusions (2a)01:06:57
Interim Conclusions (2b)01:08:08
Interim Conclusions (2c)01:08:57
Interim Conclusions (2d)01:09:31
Interim Conclusions (2e)01:10:50
Interim Conclusions (2f)01:11:33
301:13:02
Tone-in-Noise Detection01:13:33
System Identification Re-Visited (1)01:16:03
System Identification Re-Visited (2)01:16:10
System Identification Re-Visited (3)01:16:20
System Identification Re-Visited (4)01:16:22
System Identification Re-Visited (5)01:16:29
Synthetic Observers (i.e. Simulated Features)01:16:33
Observer Reconstruction—Feature Weights01:22:18
Observer Reconstruction—Inferred Filter Shapes01:22:47
Classifier performance (1)01:25:19
Classifier performance (2)01:27:40
Classifier performance (3)01:27:44
Literature (Heavily Biased Sample)01:27:44