290T: Mind-Reading and Telepathy for Beginners and Intermediates

Table of Contents

Course description

To what extent can a machine know the inner workings of a person's mind, even theoretically? This course explores this question through a mixture of hands-on machine learning and critical discussions on theory. In this course, students will practice ML techniques on a provided corpus of data to produce a working brain-computer interface. Simultaneously, students will engage critically with recent research in ubiquitous sensing technologies, and the discourse around them, tracing ideas to their origins in cognitive science.

This half-semester course runs for the first eight weeks of the semester (8/23/17 - 10/17/17).

Each week will cover one topic in mind-reading machines. Thursday classes will be a lecture, a survey of the week's readings, centering around one or two particular papers. Tuesday classes will be lab-time, centered around supporting assignments, projects and hands-on engagement with the course dataset.

This class is a pre-requisite for Info 290T. Projects on Mind-Reading Machines, an (optional) 1-unit course taking place in the second half of the semester, which would continue the themes of this course through a student-led research project.

Pre-requisites: Information 206, or knowledge of programming and data structures with consent of instructor.

Meeting time

Classes are Tuesday & Thursday 2-3:30pm, South Hall 205.


Nick Merrill
Office: 2 South Hall
Office hours: Thursdays 1p-2p, 302 South Hall, and by email appointment

John Chuang
Office: 303A South Hall
Office hours: Tuesdays 3:30-4:30pm, 303A South Hall, and by email appointment

Tentative Grading Criteria

This class will have three assignments, which prepares students for their final project. Students may work in groups on assignments and the project.

  • Lab 0 (5%)
  • Lab 1 (25%)
  • Lab 2 (25%)
  • Project proposal or written synthesis (30%)
  • Participation (15%)

Academic Integrity

Discussion with instructors and classmates is allowed/encouraged, but each student must turn in individual, original work and cite sources where appropriate.

UC Berkeley Code of Student Conduct: http://sa.berkeley.edu/code-of-conduct


Disclaimer: Schedule and readings should be considered tentative, and subject to change.

Introduction, mind <2017-08-24 Thu>


Bruno Latour (1995). Cogito ergo sumus! or psychology swept inside out by the fresh air of the upper deck. A review of Ed Hutchins Cognition in the Wild, MIT Press, in Mind, Culture, and Activity: An International Journal , Vol.3, n°1, pp.54-63


Haynes, J.-D., & Rees, G. (2006). Decoding mental states from brain activity in humans. Nature Reviews. Neuroscience, 7(7), 523–534.

Clark, A. (2013). Whatever next? Predictive brains, situated agents, and the future of cognitive science. The Behavioral and Brain Sciences, 36(3), 181–204. Zeman, Adam. Chapter 1 of Consciousness: A User's Guide London, US: Yale University Press, 2002. ProQuest ebrary. Web. 4 January 2017.

Aharony, Nadav, et al. Social fMRI: Investigating and shaping social mechanisms in the real world. Pervasive and Mobile Computing 7.6 (2011): 643-659.

Kendrick N Kay and Jack L Gallant. 2009. I can see what you see. Nature neuroscience 12, 3: 245.

Farah, M. J. (2014). Brain Images, Babies, and Bathwater: Critiquing Critiques of Functional Neuroimaging. Hastings Center Report, 44(SUPPL2), S19–S30.

Lab 1 <2017-08-29 Tue>

DUE: Lab 0

Intro to brainwaves & brain-computer interfaces <2017-08-31 Thu>


Graimann, Allison, and Pfurtscheller. Chapter 1 "Brain-Computer Interfaces: A Gentle Introduction", In: Brain-Computer Interfaces: Revolutionizing Human-Computer Interaction, Graimann et al. (Eds.), Springer, 2010. (Also: look over the Table of Contents of the book and skim other chapters that look interesting to you.)


Urban, T (2017). Neuralink and the Brain’s Magical Future. Retrieved July 31, 2017.

Grau, C et al. (2014). Conscious brain-to-brain communication in humans using non-invasive technologies. PLoS ONE 9, 8: e105225.

Seo, Dongjin, et al. "Neural dust: An ultrasonic, low power solution for chronic brain-machine interfaces." arXiv preprint arXiv:1307.2196 (2013).

Lab 1 discussion <2017-09-05 Tue>

Affect, mood, emotion <2017-09-07 Thu>


Kirsten Boehner, Rogerio DePaula, Paul Dourish, and Phoebe Sengers. (2007). How Emotion is Made and Measured. Int. J. Hum.-Comput. Stud. 65, 4 (April 2007), 275-291.

WARNING: Upsetting/violent anecodte mentioned. Leahu, L., & Sengers, P. (2014). Freaky: Collaborative Enactments of Emotion. In Proceedings of the 2014 conference on Designing interactive systems - DIS ’14 (pp. 607–616). ACM Press.


Barb Darrow. (2015). Computers can’t read your mind yet, but they’re getting closer. Fortune, September 2015.

R. W. Picard and J. Healey. (1997). Affective wearables. Personal and Ubiquitous Computing 1, 4: 231–240.

Jennifer Healey. 2014. Physiological Sensing of Emotion. The Oxford Handbook of Affective Computing, October: 204.

Parkinson, B. (2014). Emotions in Interpersonal Life. The Oxford Handbook of Affective Computing., (October), 68–83.

Lab 2 <2017-09-12 Tue>

DUE: Lab 1

Last ten minutes: Discuss final projects for independent study

Identity, authentication, mind, the self <2017-09-14 Thu>

DUE: Decide on independent study signups.


Merrill, N., Curran, M. & Chuang, J (2017). Is the Future of Authenticity All in Our Heads? Moving Passthoughts From the Lab to the World. NSPW 2017 (to appear).


Dumit, J. (2004). Picturing Personhood: Brain Scans and Biomedical Identity. Information Series, 251.

Martinovic, I, et al. (2012). "On the Feasibility of Side-Channel Attacks with Brain-Computer Interfaces." USENIX security symposium.

Bojinov, H, et al. (2012). "Neuroscience Meets Cryptography: Designing Crypto Primitives Secure Against Rubber Hose Attacks." USENIX Security Symposium.

Lab 2 discussion <2017-09-19 Tue>

Last ten minutes: Discuss final projects for independent study

How to sense a mind? <2017-09-21 Thu>


Nikolas Rose. 2016. Reading the Human Brain: How the Mind Became Legible. Body & Society 22, 2: 1–38.


Canzian, L., & Musolesi, M. (2015). Trajectories of depression. Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing - UbiComp ’15, 1293–1304.

Aharony, N., Pan, W., Ip, C., Khayal, I., & Pentland, A. (2011). The social fMRI. Proceedings of the 13th International Conference on Ubiquitous Computing - UbiComp ’11, 445.

Burleson, W. (2012). Predicting Creativity in the Wild: Experience Sample and Sociometric Modeling of Teams. In CSCW ’12: Proceedings of the ACM 2012 conference on Computer Supported Cooperative Work (pp. 1203–1212). ACM.

Eagle, N., & Pentland, A. (2006). Reality mining: Sensing complex social systems. Personal and Ubiquitous Computing, 10(4), 255–268.

Montjoye, Y. De, Quoidbach, J., Robic, F., & Pentland, A. (Sandy). (2013). Predicting Personality Using Novel Mobile Phone-Based Metrics. In A. M. Greenberg, W. G. Kennedy, & N. D. Bos (Eds.), International Conference on Social Computing, Behavioral-Cultural Modeling, & Prediction (pp. 48–55). Springer Berlin Heidelberg.

Lab: Synthesis / project proposals <2017-09-26 Tue>

DUE: Lab 2

Social interpretation(s) of sensor data <2017-09-28 Thu>


Howell, N, et al. Biosignals as Social Cues: Ambiguity and Emotional Interpretation in Social Displays of Skin Conductance.

Ali, S. S., Lifshitz, M., & Raz, A. (2014). Empirical neuroenchantment: from reading minds to thinking critically. Frontiers in Human Neuroscience, 8(May), 357.


Merrill, N, & Cheshire, C. Trust Your Heart: Assessing cooperation and trust with biosignals in computer-mediated interactions. CSCW 2017.

Elsden, C. et al. (2016). Metadating. Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems - CHI ’16: 685–698.

Joanne McNell. 2015. Who Sexts Thumbprints? Retrieved July 31, 2017.

Snyder, Jaime, et al. MoodLight: Exploring Personal and Social Implications of Ambient Display of Biosensor Data. Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing. ACM, 2015. (Note: Read up to the end of Related Work Section (p. 145), skim the middle sections, and then read from the Discussion Section (p. 150) until the end of the paper.)

Anderson, K., Nafus, D., & Rattenbury, T. (2009). Numbers Have Qualities Too: Experiences with Ethno-Mining. EPIC 2009 Proceedings, 2009(1), 123–140.

Guest lecture: Richmond Wong on speculative fiction <2017-10-03 Tue>

Lab: Synthesis / project proposals <2017-10-05 Thu>

Due: (Ind. study) Project team metadata

In-class: (Synthesis groups) Argument summary

Security & privacy <2017-10-10 Tue>

When Does Law Enforcement's Demand to Read Your Data Become a Demand to Read Your Mind? Andrew Conway, Peter Eckersley. Communications of the ACM, Vol. 60 No. 9, Pages 38-40. September 2017.

On the Feasibility of Side-Channel Attacks with Brain-Computer Interfaces Ivan Martinovic, Doug Davies, Mario Frank, Daniele Perito, Tomas Ros, Dawn Song USENIX Security Symposium 2012


A Window into the Soul: Biosensing in Public Elaine Sedenberg, Richmond Wong, John Chuang

Privacy for Personal Neuroinformatics Arkadiusz Stopczynski, Dazza Greenwood, Lars Kai Hansen, Alex Sandy Pentland arXiv:1403.2745v1 [cs.CY] 11 Mar 2014

Hacking the brain: brain–computer interfacing technology and the ethics of neurosecurity Marcello Ienca, Pim Haselager Ethics and Information Technology, April 2016 DOI 10.1007/s10676-016-9398-9

Using EEG-Based BCI Devices to Subliminally Probe for Private Information Mario Frank, Tiffany Hwu, Sakshi Jain, Robert T. Knight, Ivan Martinovic, Prateek Mittal, Daniele Perito, Ivo Sluganovic, Dawn Song arXiv:1312.6052v2 [cs.CR] 30 May 2017

Project proposal presentations <2017-10-12 Thu>

Project groups present 1-slide summary

Software requirements

You will need some software to run the labs:

  • Python 3. In a terminal window, try typing python3 --version. If it reads some number > 3, you are good to go! If not, install Python3.6 for your platform.
  • Jupyter notebooks. You can download the notebook installer here.
  • XGBoost. You can follow the setup instructions on the XGBoost documentation. Clone the repository, build the source, and perform the steps in "Python package installation." (We can provide support on this during the first lab session).
  • sklearn and pandas. You should be able to simply pip3 install sklearn pandas.

Author: ffff

Created: 2017-10-03 Tue 19:36