Ryan Eberhardt invited Xpanse to give a guest lecture on the last day of a summer session of Stanford CS 110, in that gap between real coursework and the final.

CS 110 is the second course in Stanford’s systems programming sequence. I loved taking it as a student. I loved CS 110 so much that I TAed it twice, even though it’s a really tough course to TA (the students are zillions of new undergrads, there’s a lot of assignments to give feedback on, and the material is pretty hard for them so office hours consist of a never-ending queue of students with questions). My professor Jerry Cain gave me an award for my TA work, so hopefully I did okay by them.

For this re-visit to CS 110, I introduced microservices, containerization, and orchestration. I gave the orientation to why they should care and who we were. Then two sharp coworkers talked about their daily tech of port scanning and functional programming. I concluded the lecture with hinting at the problems solved by Docker and Kubernetes (and the problems created by them), and I asked leading questions that extended some of the core ideas in CS 110: decoupling of concerns, each worker does one thing, pools of workers share a single point of entry, and request/response models.

My final project for Stanford CS 224S was on subvocal speech recognition. This was my last paper at Stanford; it draws on everything I learned in a whirlwind of CS grad school without a CS undergraduate major. Pol Rosello provided the topic; he and I contributed equally to the paper.

We describe the first approach toward end-to-end, session-independent subvocal automatic speech recognition from involuntary facial and laryngeal muscle movements detected by surface electromyography. We leverage character-level recurrent neural networks and the connectionist temporal classification loss (CTC). We attempt to address challenges posed by a lack of data, including poor generalization, through data augmentation of electromyographic signals, a specialized multi-modal architecture, and regularization. We show results indicating reasonable qualitative performance on test set utterances, and describe promising avenues for future work in this direction.

We spend a lot of time talking about supervised learning when discussing ML with students, but I find reinforcement learning just as interesting and useful.

I developed a talk on reinforcement learning for high school participants in SAIL ON, the year-round diversity and high school outreach program of the Stanford AI Lab that I initiated and led, which follows the SAILORS intensive two-week AI summer camp.

We discuss how reinforcement learning works, how to make decisions given Bayesian bounds, touchstone RL problems and recent applications, and where RL tends to succeed and fail.

My final project for Stanford CS 224N was on hybrid word-character machine translation for Arabic.

Traditional models of neural machine translation make the false-but-true-in-English assumption that words are essentially equivalent to units of meaning. Morphologically rich languages disobey this assumption. We implement a hybrid translation model that backs off unknown words to a representation created by modeling their constituent characters in TensorFlow, we apply the model to Arabic translation, and approach state-of-the-art performance for Arabic over the weeks allotted for a class project.

I gave the keynote address at Byte Sized, a workshop for middle school girls spearheaded by SAIL ON students. My First AI (or: Decision Trees & Language Modeling for Middle Schoolers) solidified the basics of artificial intelligence and the if/else statements taught the previous day.

The talk introduces the language identification problem within AI, teaches about decision trees, and then asks students to write decision trees in small groups to distinguish between Hmong, Balinese, Zulu, and other languages. After a debrief on why computers are might be more effective than human-written rules, it briefly ties in themes of feature extraction and gradient descent via GBMs.