Appendix H. Course Syllabi

This book covers fourteen parts and seventy-two chapters, which is more than any single term can hold. This appendix carves five teachable tracks out of that material, each aimed at a different audience and calendar. Every track lists the chapters it uses, so you can assemble reading and lab schedules directly from the table of contents. The first two tracks are given as full week-by-week tables that map each session to book parts and chapters; the remaining three are given as compact chapter-to-week maps that you can expand the same way. A standard week is one topic lecture plus one graded lab, and every track ends with a project rather than a final exam, because a sensor system is only understood once it has been built and evaluated on data it has not seen.

Track 1: Undergraduate Sensory AI (14 weeks)

A first course for third-year or fourth-year students who have taken linear algebra, probability, and one machine-learning course. It walks the classical-to-neural arc for one-dimensional sensor streams and stops before foundation models. The project is a wearable activity recognizer evaluated leave-one-subject-out.

WkTopicBookLab
1What sensory AI is; the sense-model-act loopCh 1Read a live IMU stream, plot and annotate it
2Sensor physics and measurement modelsCh 2Fit a calibration curve to a noisy sensor
3Signals, sampling, aliasing, synchronizationCh 3Alias a signal on purpose, then fix the rate
4Probability, estimation, uncertaintyCh 4Maximum-likelihood fit with error bars
5Data engineering and leakage-safe splitsCh 5Build a subject-grouped train/test split
6Filtering and denoisingCh 6Low-pass and median filters on real motion data
7Spectral and time-frequency analysisCh 7Spectrogram of gait; read cadence off it
8Feature engineering and dimensionality reductionCh 8Handcrafted features plus PCA baseline
9Bayesian filtering and the Kalman familyCh 91D Kalman filter for a drifting sensor
10Neural representations for sensor streamsCh 131D CNN on windowed accelerometer data
11Recurrent and temporal convolutional modelsCh 14Compare an LSTM and a TCN on the same task
12Inertial sensors; human activity recognitionCh 23, 26Full HAR pipeline on UCI-HAR
13Uncertainty, calibration, conformal predictionCh 18Calibrate the HAR model; add conformal sets
14Evaluation protocols; project presentationsCh 65Leave-one-subject-out report and defense

The leakage discipline of week 5 is the spine of the course: every later lab is graded partly on whether the split keeps each subject on one side of the boundary. Formally the model is scored on \(\mathbb{E}_{s \notin \mathcal{S}_{\text{train}}}[\ell]\), the expected loss over subjects never seen in training, which is the only number that predicts field behavior.

Track 2: Graduate Cyber-Physical and Foundation-Model Sensing (14 weeks)

A research-oriented graduate seminar assuming a solid deep-learning background. It pairs modern sequence architectures with foundation models and closes the loop on trust, cyber-physical security, and fleet operations. Each week combines a lecture, one paper the class critiques, and a lab; the project is an original benchmark or method on a leakage-safe cyber-physical dataset.

WkTopicBookLab
1Leakage-safe datasets and evaluation, revisited hardCh 5, 65Break a published split; measure the inflation
2Factor graphs and smoothing for state estimationCh 11Batch smoothing on a trajectory with a solver
3Transformers for sensor dataCh 15Patch-and-attend model on multivariate series
4State-space models: S4, Mamba, linear-time sequencesCh 16Reproduce a long-context SSM baseline
5Self-supervised and contrastive sensor learningCh 17Pretrain with masking; probe the frozen encoder
6Time-series foundation modelsCh 19Zero-shot forecast; guard against contamination
7Sensor and wearable foundation modelsCh 20Fine-tune a sensor FM on a small labeled set
8Multimodal sensor-language models and reasoningCh 21Caption and query a sensor window with an SLM
9LLM agents for sensing and operationsCh 22Agent that triages alarms from a telemetry feed
10Deep multimodal fusion; missing-modality robustnessCh 50Drop a modality at test time; measure the fall
11Distribution shift, OOD, test-time adaptationCh 66Adapt a model to an unseen operating regime
12Cyber-physical anomaly detection and ICS securityCh 38Event-level anomaly scoring on SWaT or WADI
13Robustness, sensor spoofing, functional safetyCh 68Craft a spoof; test detector and safety envelope
14MLOps for sensor fleets; project defenseCh 69Ship the project with drift monitoring

Week 12 is deliberate about metrics: on ICS datasets attacks appear only in the test window, so point-adjusted accuracy can turn one lucky detection into a near-perfect score. The seminar requires range-based scoring, and asks students to report both the naive and the honest number so the gap is visible.

Track 3: IoT and Edge AI Professional Course (7 weeks)

A short, hands-on course for working engineers who need to deploy models on constrained hardware. It skips most classical theory and drives toward a microcontroller demo. Assumes Python fluency and basic ML.

WkTopicBook
1Sensory AI overview; sensor data engineeringCh 1, 5
2Neural representations for sensor streamsCh 13, 14
3Edge AI fundamentals and model optimizationCh 59
4Streaming inference and online learningCh 60
5TinyML and microcontroller sensor AICh 61
6On-device continual learning; batteryless sensingCh 62, 63
7Federated and privacy-preserving sensor AI; capstoneCh 64

The capstone is a quantized keyword or gesture spotter running on a microcontroller under a fixed memory and latency budget, reported as an accuracy-versus-\(\text{flash}\times\text{latency}\) frontier rather than a single accuracy number.

Track 4: Robotics Sensor Fusion and Embodied AI Seminar (14 weeks)

A graduate seminar for robotics students, pairing geometric perception with learned world models and embodied policies. It reads roughly one part per fortnight and builds toward a fusion-and-navigation project on a real or simulated platform.

WkTopicBook
1Orientation estimation and dead reckoningCh 24
2Localization, GNSS, RF positioningCh 25
3Depth and 3D sensing fundamentalsCh 40
4Point clouds and LiDAR AICh 42
5BEV perception and 3D occupancyCh 43
6Foundations of sensor fusionCh 48
7Probabilistic and Bayesian fusionCh 49
8Neural fields and Gaussian splatting for sensingCh 51
9SLAM and spatial AICh 52
10World models and predictive sensingCh 53
11Tactile sensing and electronic skinCh 56
12Proprioception, exteroception, robot perceptionCh 57
13Vision-language-action and embodied foundation modelsCh 58
14Integration and project defenseCh 71, 72

Track 5: Health and Wearable AI Short Course (7 weeks)

A short course for biomedical or data-science students focused on biosignals and the regulatory reality that surrounds them. Subject-independent evaluation is non-negotiable throughout, and the project is a wearable cardiovascular estimator with a validation and privacy write-up.

WkTopicBook
1Biosignal foundations; signals and samplingCh 3, 28
2ECG and cardiac AICh 29
3PPG and wearable cardiovascular sensingCh 30
4EMG and neuromuscular AICh 32
5Continuous and contactless health monitoringCh 33
6Uncertainty, calibration, conformal predictionCh 18
7Clinical validation, regulation, biometric privacy; capstoneCh 34

Across every track, three rules travel with the course and should appear on the first slide of each. Split on the group, never on the window, so the reported number measures generalization and not memory. Report uncertainty alongside every point estimate, because a sensor decision without a confidence is not actionable. And evaluate on the shift you actually care about, whether that shift is a new subject, a new machine, a new room, or a new day. A student who leaves with those three habits has learned the part of sensory AI that outlasts any particular architecture.