Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Upcoming SlideShare
What to Upload to SlideShare
Next
Download to read offline and view in fullscreen.

Share

Understanding Information Processing in Human Brain by Interpreting Machine Learning Models - PhD Defense Slides

Download to read offline

The thesis explores the role machine learning methods play in creating intuitive computational models of neural processing. Combined with interpretability techniques, machine learning could replace human modeler and shift the focus of human effort to extracting the knowledge from the ready-made models and articulating that knowledge into intuitive descriptions of reality. This perspective makes the case in favor of the larger role that exploratory and data-driven approach to computational neuroscience could play while coexisting alongside the traditional hypothesis-driven approach.
We exemplify the proposed approach in the context of the knowledge representation taxonomy with three research projects that employ interpretability techniques on top of machine learning methods at three different levels of neural organization. The first study (Chapter 3) explores feature importance analysis of a random forest decoder trained on intracerebral recordings from 100 human subjects to identify spectrotemporal signatures that characterize local neural activity during the task of visual categorization. The second study (Chapter 4) employs representation similarity analysis to compare the neural responses of the areas along the ventral stream with the activations of the layers of a deep convolutional neural network. The third study (Chapter 5) proposes a method that allows test subjects to visually explore the state representation of their neural signal in real time. This is achieved by using a topology-preserving dimensionality reduction technique that allows to transform the neural data from the multidimensional representation used by the computer into a two-dimensional representation a human can grasp.
The approach, the taxonomy, and the examples, present a strong case for the applicability of machine learning methods to automatic knowledge discovery in neuroscience.

Related Books

Free with a 30 day trial from Scribd

See all

Related Audiobooks

Free with a 30 day trial from Scribd

See all
  • Be the first to like this

Understanding Information Processing in Human Brain by Interpreting Machine Learning Models - PhD Defense Slides

  1. 1. Understanding Information Processing in Human Brain by Interpreting Machine Learning Models Ilya Kuzovkin All models are wrong, but some are useful.
 
 – George E. P. Box Supervised by Raul Vicente
  2. 2. http://ircamera.as.arizona.edu/NatSci102/NatSci102/lectures/kepler.htm https://www.helioseducore.com/keplers-laws-of-planetary-motion Modeling is a well-proven way of obtaining knowledge https://www.forbes.com/sites/andrewbusby/2019/03/04/new-pwc-survey-reveals-consumer-data-is-the-most-highly-valued/#6a084d3d640c https://cs.hse.ru/en/bayesgroup/education/momlhttps://towardsdatascience.com/black-boxes-and-their-intrusion-620aa3c4c56b MANUALAUTOMATED
  3. 3. http://ircamera.as.arizona.edu/NatSci102/NatSci102/lectures/kepler.htm Johannes KeplerTycho Brahe's observations 27 years D A T A A L G O R I T H M M O D E L https://www.helioseducore.com/keplers-laws-of-planetary-motion Modeling is a well-proven way of obtaining knowledge Three Laws of Planetary Motion https://www.forbes.com/sites/andrewbusby/2019/03/04/new-pwc-survey-reveals-consumer-data-is-the-most-highly-valued/#6a084d3d640c https://cs.hse.ru/en/bayesgroup/education/momlhttps://towardsdatascience.com/black-boxes-and-their-intrusion-620aa3c4c56b MANUALAUTOMATED
  4. 4. http://ircamera.as.arizona.edu/NatSci102/NatSci102/lectures/kepler.htm Johannes KeplerTycho Brahe's observations 27 years D A T A A L G O R I T H M M O D E L https://www.helioseducore.com/keplers-laws-of-planetary-motion Modeling is a well-proven way of obtaining knowledge Three Laws of Planetary Motion Some data https://www.forbes.com/sites/andrewbusby/2019/03/04/new-pwc-survey-reveals-consumer-data-is-the-most-highly-valued/#6a084d3d640c A machine learning algorithm The model https://cs.hse.ru/en/bayesgroup/education/momlhttps://towardsdatascience.com/black-boxes-and-their-intrusion-620aa3c4c56b Black
 box
 model MANUALAUTOMATED
  5. 5. http://ircamera.as.arizona.edu/NatSci102/NatSci102/lectures/kepler.htm Johannes KeplerTycho Brahe's observations 27 years D A T A A L G O R I T H M M O D E L https://www.helioseducore.com/keplers-laws-of-planetary-motion Modeling is a well-proven way of obtaining knowledge Three Laws of Planetary Motion K N O W L E D G E MODEL = Some data https://www.forbes.com/sites/andrewbusby/2019/03/04/new-pwc-survey-reveals-consumer-data-is-the-most-highly-valued/#6a084d3d640c A machine learning algorithm The model IT'S THERE
 BUT
 HIDDEN https://cs.hse.ru/en/bayesgroup/education/momlhttps://towardsdatascience.com/black-boxes-and-their-intrusion-620aa3c4c56b Black
 box
 model MANUALAUTOMATED
  6. 6. http://ircamera.as.arizona.edu/NatSci102/NatSci102/lectures/kepler.htm Johannes KeplerTycho Brahe's observations 27 years D A T A A L G O R I T H M M O D E L https://www.helioseducore.com/keplers-laws-of-planetary-motion Modeling is a well-proven way of obtaining knowledge Three Laws of Planetary Motion K N O W L E D G E MODEL = Some data https://www.forbes.com/sites/andrewbusby/2019/03/04/new-pwc-survey-reveals-consumer-data-is-the-most-highly-valued/#6a084d3d640c A machine learning algorithm The model IT'S THERE
 BUT
 HIDDEN https://cs.hse.ru/en/bayesgroup/education/momlhttps://towardsdatascience.com/black-boxes-and-their-intrusion-620aa3c4c56b Black
 box
 model Machine learning can uncover knowledge Model interpretation is required to articulate it MANUALAUTOMATED
  7. 7. In life sciences model interpretation has a special significance https://www.sciencenewsforstudents.org/article/life-earth-mostly-green https://www.youtube.com/watch?v=Evsqy0a_Lrk https://www.sciencemag.org/news/2018/08/scientists-tweak-dna-viable-human-embryos https://astronomy.com/news/2019/01/maybe-you-really-can-use-black-holes-to-travel-the-universe https://www3.mpifr-bonn.mpg.de/staff/rbeck/MKSP/pictures.html http://andysbrainblog.blogspot.com/2015/04/slice-analysis-of-fmri-data-with-spm.html https://www.wired.com/story/the-rise-of-dna-data-storage/
  8. 8. In life sciences model interpretation has a special significance Interpretability in ML • Trust in model's decision • Legal transparency • Debugging https://www.sciencenewsforstudents.org/article/life-earth-mostly-green https://www.youtube.com/watch?v=Evsqy0a_Lrk https://www.sciencemag.org/news/2018/08/scientists-tweak-dna-viable-human-embryos https://astronomy.com/news/2019/01/maybe-you-really-can-use-black-holes-to-travel-the-universe https://www3.mpifr-bonn.mpg.de/staff/rbeck/MKSP/pictures.html http://andysbrainblog.blogspot.com/2015/04/slice-analysis-of-fmri-data-with-spm.html https://www.wired.com/story/the-rise-of-dna-data-storage/
  9. 9. In life sciences model interpretation has a special significance Interpretability in ML • Trust in model's decision • Legal transparency • Debugging https://www.sciencenewsforstudents.org/article/life-earth-mostly-green https://www.youtube.com/watch?v=Evsqy0a_Lrk https://www.sciencemag.org/news/2018/08/scientists-tweak-dna-viable-human-embryos https://astronomy.com/news/2019/01/maybe-you-really-can-use-black-holes-to-travel-the-universe A model that can make correct predictions about reality Black
 box
 model https://www3.mpifr-bonn.mpg.de/staff/rbeck/MKSP/pictures.html http://andysbrainblog.blogspot.com/2015/04/slice-analysis-of-fmri-data-with-spm.html https://www.wired.com/story/the-rise-of-dna-data-storage/
  10. 10. In life sciences model interpretation has a special significance At this point the model knows something about the world that the scientist does not Interpretability in ML • Trust in model's decision • Legal transparency • Debugging https://www.sciencenewsforstudents.org/article/life-earth-mostly-green https://www.youtube.com/watch?v=Evsqy0a_Lrk https://www.sciencemag.org/news/2018/08/scientists-tweak-dna-viable-human-embryos https://astronomy.com/news/2019/01/maybe-you-really-can-use-black-holes-to-travel-the-universe A model that can make correct predictions about reality Black
 box
 model https://www3.mpifr-bonn.mpg.de/staff/rbeck/MKSP/pictures.html http://andysbrainblog.blogspot.com/2015/04/slice-analysis-of-fmri-data-with-spm.html https://www.wired.com/story/the-rise-of-dna-data-storage/
  11. 11. In life sciences model interpretation has a special significance At this point the model knows something about the world that the scientist does not Interpretability in ML • Trust in model's decision • Legal transparency • Debugging • Articulating the knowledge about the underlying process that the model has captured https://www.sciencenewsforstudents.org/article/life-earth-mostly-green https://www.youtube.com/watch?v=Evsqy0a_Lrk https://www.sciencemag.org/news/2018/08/scientists-tweak-dna-viable-human-embryos https://astronomy.com/news/2019/01/maybe-you-really-can-use-black-holes-to-travel-the-universe A model that can make correct predictions about reality Black
 box
 model https://www3.mpifr-bonn.mpg.de/staff/rbeck/MKSP/pictures.html http://andysbrainblog.blogspot.com/2015/04/slice-analysis-of-fmri-data-with-spm.html https://www.wired.com/story/the-rise-of-dna-data-storage/
  12. 12. In life sciences model interpretation has a special significance At this point the model knows something about the world that the scientist does not Interpretability in ML • Trust in model's decision • Legal transparency • Debugging • Articulating the knowledge about the underlying process that the model has captured https://www.sciencenewsforstudents.org/article/life-earth-mostly-green https://www.youtube.com/watch?v=Evsqy0a_Lrk https://www.sciencemag.org/news/2018/08/scientists-tweak-dna-viable-human-embryos https://astronomy.com/news/2019/01/maybe-you-really-can-use-black-holes-to-travel-the-universe A model that can make correct predictions about reality Black
 box
 model https://www3.mpifr-bonn.mpg.de/staff/rbeck/MKSP/pictures.html http://andysbrainblog.blogspot.com/2015/04/slice-analysis-of-fmri-data-with-spm.html https://www.wired.com/story/the-rise-of-dna-data-storage/ Machine-learned models
 as scientific theories
 • Both capture and model observations • Both make correct predictions
 on new observations • Computers can generate and test theories faster than humans • In the big data regime there is not enough scientists to sift through all potential explanations of the data • Algorithms have different bias than humans, hence find different solutions
  13. 13. "Identifying task-relevant spectral signatures of perceptual categorization in the human cortex"
 Scientific Reports, 2020 "Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex"
 Communications Biology, 2018 "Mental state space visualization for interactive modeling of personalized BCI control strategies"
 Journal of Neural Engineering, 2020 Applying this principle in Neuroscience
  14. 14. Identifying task-relevant spectral signatures of perceptual categorization in the human visual cortex 100 patients
 12,000 electrodes
  15. 15. Identifying task-relevant spectral signatures of perceptual categorization in the human visual cortex 100 patients
 12,000 electrodes 4,528,400 responses 400 images from 8 categories
  16. 16. Identifying task-relevant spectral signatures of perceptual categorization in the human visual cortex 100 patients
 12,000 electrodes 4,528,400 responses 400 images from 8 categories x = {f1, f2, . . . , f3504, . . . , f7008}
  17. 17. Identifying task-relevant spectral signatures of perceptual categorization in the human visual cortex 100 patients
 12,000 electrodes 4,528,400 responses 400 images from 8 categories x = {f1, f2, . . . , f3504, . . . , f7008} Which parts of this brain activity are generated by the underlying process of mental image categorization?
  18. 18. Identifying task-relevant spectral signatures of perceptual categorization in the human visual cortex 100 patients
 12,000 electrodes 4,528,400 responses 400 images from 8 categories x = {f1, f2, . . . , f3504, . . . , f7008} Feature importance map Which parts of this brain activity are generated by the underlying process of mental image categorization?
  19. 19. Identifying task-relevant spectral signatures of perceptual categorization in the human visual cortex Multiple brain regions respond when a stimulus is shown, but only a small fraction (5%) are predictive of a category.
  20. 20. Identifying task-relevant spectral signatures of perceptual categorization in the human visual cortex While some locations are predictive of multiple visual categories, others have narrow specialization.
  21. 21. Identifying task-relevant spectral signatures of perceptual categorization in the human visual cortex
  22. 22. Identifying task-relevant spectral signatures of perceptual categorization in the human visual cortex
  23. 23. Identifying task-relevant spectral signatures of perceptual categorization in the human visual cortex It is believed that high-frequency activity reflects the information processing during high cognitive tasks. We show that low-frequency activity is almost as important for the task at hand. Across all categories the classifier relied on power decreases in different brain networks, not only on the increases to perform the classification
  24. 24. "Identifying task-relevant spectral signatures of perceptual categorization in the human cortex"
 Scientific Reports, 2020 "Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex"
 Communications Biology, 2018 "Mental state space visualization for interactive modeling of personalized BCI control strategies"
 Journal of Neural Engineering, 2020 Applying this principle in Neuroscience
  25. 25. Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex
  26. 26. Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex
  27. 27. Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex From previous fMRI research we knew that there is a mapping between the hierarchies Intracranial electrophysiological data allowed us to learn when and at which frequencies
  28. 28. Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex
  29. 29. Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex
  30. 30. Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex
  31. 31. Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex
  32. 32. Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex
  33. 33. Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex
  34. 34. - simple features (mapped to lower layers of DCNN) - complex features (higher layers) Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex
  35. 35. - simple features (mapped to lower layers of DCNN) - complex features (higher layers) Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex
  36. 36. "Identifying task-relevant spectral signatures of perceptual categorization in the human cortex"
 Scientific Reports, 2020 "Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex"
 Communications Biology, 2018 "Mental state space visualization for interactive modeling of personalized BCI control strategies"
 Journal of Neural Engineering, 2020 Applying this principle in Neuroscience
  37. 37. Mental state space visualization for interactive modeling of personalized BCI control strategies Mental
 actions Machine learning
 algorithm Control
 commands An external
 device Brain
 signal
  38. 38. Mental state space visualization for interactive modeling of personalized BCI control strategies Mental
 actions Machine learning
 algorithm Control
 commands An external
 device Brain
 signal The algorithm must distinguish between different mental actions The user must produce mental actions that are distinguishable by the machine and do that consistently
  39. 39. Mental state space visualization for interactive modeling of personalized BCI control strategies Mental
 actions Machine learning
 algorithm Control
 commands An external
 device Neural
 signal The algorithm must distinguish between different mental actions The user must produce mental actions that are distinguishable by the machine and do that consistently If the user could see machine's representation of his mental actions he could find out which ones are suitable
  40. 40. Mental state space visualization for interactive modeling of personalized BCI control strategies
  41. 41. Mental state space visualization for interactive modeling of personalized BCI control strategies
  42. 42. Mental state space visualization for interactive modeling of personalized BCI control strategies
  43. 43. L E V E L OF N E U R A L
 O R G A N I Z A T I O N K N O W L E D G E R E P R E S E N T A I O N
 I N T H E M O D E L Random Forests:
 feature-based rules Self-Organizing Maps:
 topology of the samples DNNs: distributed representations over features (input or latent) http://news.mit.edu/2014/optogenetic-toolkit-goes-multicolor-0209 Local responses of a neural population Hierarchy of visual areas R E S E A R C H
 P R O J E C T Kuzovkin et al.,
 "Identifying task-relevant spectral signatures of perceptual categorization in the human cortex"
 Scientific Reports, 2020 (in review) Kuzovkin et al.,
 "Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex"
 Communications Biology, 2018 Kuzovkin et al.,
 "Mental state space visualization for interactive modeling of personalized BCI control strategies"
 Journal of Neural Engineering, 2020 Correlates of mental states
 ("thoughts")
  44. 44. Interpretability adds a new axis for algorithm selection Different machine learning algorithms capture knowledge into different representations Pick the one that will reveal the knowledge you are after,
 not the one that just gives the best performance on a metric. Support Vector Machines: points in the feature space Self-Organizing Maps:
 topology of the samples Random Forests:
 feature-based rules DNNs: distributed representations over features (input or latent) Hidden Markov Models:
 states and transitions Gaussian Processes:
 functions https://www.superdatascience.com/blogs/the-ultimate-guide-to-self-organizing-maps-somshttps://math.stackexchange.com/tags/neural-networks/info https://blog.toadworld.com/2018/08/31/random-forest-machine-learning-in-r-python-and-sql-part-1https://www.economind.org/single-post/2017/11/23/Is-Economic-Modelling-a-futile-attempt-before-the-everlasting-Uncertainty
  45. 45. Memory buffer Curiously similar mechanisms in biological and artificial systems
  46. 46. Interpreting the mechanisms of machine learning models
 can shed light on the mechanisms of the brain Memory buffer Curiously similar mechanisms in biological and artificial systems
  47. 47. • Modeling is a well-proven way of obtaining knowledge
 • Machine-learned models do capture the knowledge, but an additional step of interpretation is required
 • In life sciences model interpretation has a special significance
 • Three examples of applying this principle in Neuroscience
 
 
 
 
 
 
 
 • Interpretability adds a new axis for algorithm selection
 • Interpreting the mechanisms of machine learning models can shed light on the mechanisms of the brain "Identifying task-relevant spectral signatures of perceptual categorization in the human cortex"
 Scientific Reports, 2020 "Activations of deep convolutional neural networks are aligned with gamma band activity of human visual cortex"
 Communications Biology, 2018 "Mental state space visualization for interactive modeling of personalized BCI control strategies"
 Journal of Neural Engineering, 2020 Discussion
  48. 48. This would not be possible without the constant flow of ideas born at the seminars, lunch breaks, discussions with Anna Leontjeva, Tambet Matiisen, Jaan Aru, Ardi Tampuu, Kristjan Korjus and all lab members and alumni, students, and co-authors, the support and knowledge given by the University of Tartu and the Institute of Computer Science, Raul Vicente establishing the Computational Neuroscience Lab and supervising my PhD studies, Sven Laur further developing my understanding of machine learning, the work done by Juan R. Vidal and the co-authors from Lyon Neuroscience Research Center, Konstantin Tretyakov introducing me to the field of machine learning, my parents and family, who showed me the value of knowledge and provided with the opportunity to pursue it. Thank you!
  49. 49. Neuroscience Machine Learning & AI Aims to understand learning systems and intelligence
 by analyzing
 and reverse engineering
 the existing example Aims
 to build
 an intelligent
 system ground-up
 by figuring out the
 building blocks and rules
 of interactions between them a special kind of synergy that leads to curious similarities
  50. 50. Hippocampus Curiously similar mechanisms in biological and artificial systems Experience replay Hierarchy of visual layers An efficient spacial code Memory
 consolidation Buffer Deep Q-Learning Experience
 replay Layers of visual cortex Deep convolutional neural network • Layered structure • Hierarchy of representational complexity • Receptive fields convolutional filters Self-emergent spacial code Grid cells in entorhinal cortex Grid-based code for location

The thesis explores the role machine learning methods play in creating intuitive computational models of neural processing. Combined with interpretability techniques, machine learning could replace human modeler and shift the focus of human effort to extracting the knowledge from the ready-made models and articulating that knowledge into intuitive descriptions of reality. This perspective makes the case in favor of the larger role that exploratory and data-driven approach to computational neuroscience could play while coexisting alongside the traditional hypothesis-driven approach. We exemplify the proposed approach in the context of the knowledge representation taxonomy with three research projects that employ interpretability techniques on top of machine learning methods at three different levels of neural organization. The first study (Chapter 3) explores feature importance analysis of a random forest decoder trained on intracerebral recordings from 100 human subjects to identify spectrotemporal signatures that characterize local neural activity during the task of visual categorization. The second study (Chapter 4) employs representation similarity analysis to compare the neural responses of the areas along the ventral stream with the activations of the layers of a deep convolutional neural network. The third study (Chapter 5) proposes a method that allows test subjects to visually explore the state representation of their neural signal in real time. This is achieved by using a topology-preserving dimensionality reduction technique that allows to transform the neural data from the multidimensional representation used by the computer into a two-dimensional representation a human can grasp. The approach, the taxonomy, and the examples, present a strong case for the applicability of machine learning methods to automatic knowledge discovery in neuroscience.

Views

Total views

774

On Slideshare

0

From embeds

0

Number of embeds

664

Actions

Downloads

4

Shares

0

Comments

0

Likes

0

×