mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-07-19 09:24:14 -05:00
ed68fda58c
First-pass topic_chapter_map.yaml (87 topics → book chapters, primary + also_see + rationale) plus the design analysis for connecting each StaffML question back to recommended textbook reading. Seeds the future work tracked in harvard-edge/cs249r_book#1822. Not yet wired into the build.
401 lines
21 KiB
YAML
401 lines
21 KiB
YAML
# =============================================================================
|
||
# topic_chapter_map.yaml — StaffML topic → MLSysBook chapter map
|
||
# =============================================================================
|
||
#
|
||
# PURPOSE
|
||
# Maps each of the 87 curated topics (taxonomy_data.yaml) to the book
|
||
# chapter(s) where that subject is developed. This is a "go deeper" pointer,
|
||
# NOT an answer key: it says "if you want to learn about this topic, here's
|
||
# where the book covers it" — tied to the question's `topic`, decoupled from
|
||
# its solution. Every question inherits its reference from its topic, so this
|
||
# ~87-row file replaces per-question authoring across all 10,711 questions.
|
||
#
|
||
# STATUS
|
||
# FIRST-PASS DRAFT for review. Primary/also_see were assigned from each
|
||
# topic's taxonomy description + competency area + tracks. The author is the
|
||
# source of truth on where each concept is actually *sourced* in the book —
|
||
# fix any row whose `primary` points at the wrong chapter.
|
||
#
|
||
# SCHEMA (per topic)
|
||
# <topic-id>:
|
||
# primary: { vol: <1|2>, chapter: <slug> } # the one chapter to send a learner to
|
||
# also_see: [ { vol, chapter }, ... ] # optional, 0–2 secondary chapters
|
||
# why: "<one line: what this chapter develops for the topic>"
|
||
#
|
||
# URL DERIVED AT BUILD TIME (verified live, HTTP 200):
|
||
# https://mlsysbook.ai/vol{N}/contents/vol{N}/{chapter}/{chapter}.html
|
||
# (chapter-level only; section anchors carry regen-on-build hash suffixes)
|
||
#
|
||
# CHAPTER SLUGS (from the Quarto configs)
|
||
# Vol 1: introduction, ml_systems, ml_workflow, data_engineering,
|
||
# nn_computation, nn_architectures, frameworks, training,
|
||
# data_selection, model_compression, hw_acceleration, benchmarking,
|
||
# model_serving, ml_ops, responsible_engr, conclusion
|
||
# Vol 2: compute_infrastructure, network_fabrics, data_storage,
|
||
# distributed_training, collective_communication, fault_tolerance,
|
||
# fleet_orchestration, performance_engineering, inference,
|
||
# edge_intelligence, ops_scale, security_privacy, robust_ai,
|
||
# sustainable_ai, responsible_ai, conclusion
|
||
# =============================================================================
|
||
|
||
# ---------------------------------------------------------------- architecture
|
||
transformer-systems-cost:
|
||
primary: { vol: 1, chapter: nn_architectures }
|
||
also_see: [ { vol: 2, chapter: inference } ]
|
||
why: "Transformers and scaling laws are introduced here; KV-cache/attention cost recurs in inference."
|
||
cnn-efficient-design:
|
||
primary: { vol: 1, chapter: nn_architectures }
|
||
also_see: [ { vol: 1, chapter: model_compression } ]
|
||
why: "Depthwise-separable / MobileNet design lives in the architectures chapter."
|
||
attention-scaling:
|
||
primary: { vol: 1, chapter: nn_architectures }
|
||
also_see: [ { vol: 2, chapter: inference } ]
|
||
why: "MHA/GQA/MQA variants are an architecture topic; context-length cost shows up at inference."
|
||
mixture-of-experts:
|
||
primary: { vol: 1, chapter: nn_architectures }
|
||
also_see: [ { vol: 2, chapter: distributed_training } ]
|
||
why: "MoE as an architecture; expert parallelism is a distributed-training concern."
|
||
model-size-estimation:
|
||
primary: { vol: 1, chapter: nn_architectures }
|
||
also_see: [ { vol: 1, chapter: model_compression } ]
|
||
why: "Parameter counting and footprint feasibility follow from the architecture."
|
||
neural-architecture-search:
|
||
primary: { vol: 1, chapter: nn_architectures }
|
||
also_see: [ { vol: 2, chapter: edge_intelligence } ]
|
||
why: "NAS is architectural; hardware-aware/MCUNet-style search is an edge topic."
|
||
encoder-decoder-tradeoffs:
|
||
primary: { vol: 1, chapter: nn_architectures }
|
||
why: "Encoder-only vs decoder-only vs enc-dec is a core architectures discussion."
|
||
recommendation-systems-engineering:
|
||
primary: { vol: 1, chapter: nn_architectures }
|
||
also_see: [ { vol: 1, chapter: model_serving }, { vol: 2, chapter: data_storage } ]
|
||
why: "RecSys architecture; embedding-table scale touches serving and storage."
|
||
|
||
# --------------------------------------------------------------------- compute
|
||
roofline-analysis:
|
||
primary: { vol: 1, chapter: hw_acceleration }
|
||
also_see: [ { vol: 2, chapter: performance_engineering } ]
|
||
why: "The roofline model is introduced with accelerators; reused for perf tuning at scale."
|
||
gpu-compute-architecture:
|
||
primary: { vol: 1, chapter: hw_acceleration }
|
||
also_see: [ { vol: 2, chapter: compute_infrastructure } ]
|
||
why: "Warps/occupancy/Tensor Cores are taught in the hardware-acceleration chapter."
|
||
accelerator-comparison:
|
||
primary: { vol: 1, chapter: hw_acceleration }
|
||
also_see: [ { vol: 2, chapter: compute_infrastructure } ]
|
||
why: "CPU/GPU/TPU/NPU/ASIC spectrum is the heart of hardware acceleration."
|
||
mcu-compute-constraints:
|
||
primary: { vol: 2, chapter: edge_intelligence }
|
||
also_see: [ { vol: 1, chapter: hw_acceleration } ]
|
||
why: "MCU/no-FPU/CMSIS-NN constraints are a TinyML (edge) deployment topic."
|
||
systolic-dataflow:
|
||
primary: { vol: 1, chapter: hw_acceleration }
|
||
also_see: [ { vol: 2, chapter: compute_infrastructure } ]
|
||
why: "Systolic arrays and weight/output-stationary dataflows are accelerator internals."
|
||
compute-cost-estimation:
|
||
primary: { vol: 1, chapter: hw_acceleration }
|
||
also_see: [ { vol: 2, chapter: compute_infrastructure } ]
|
||
why: "FLOPs/GPU-hours/$ estimation builds on the accelerator cost model."
|
||
chiplet-architecture:
|
||
primary: { vol: 2, chapter: compute_infrastructure }
|
||
also_see: [ { vol: 1, chapter: hw_acceleration } ]
|
||
why: "Multi-die scaling and yield-cost tradeoffs are a fleet-scale compute topic."
|
||
|
||
# ---------------------------------------------------------------- cross-cutting
|
||
federated-learning:
|
||
primary: { vol: 2, chapter: edge_intelligence }
|
||
also_see: [ { vol: 2, chapter: security_privacy } ]
|
||
why: "Cross-device FL is an edge topic; privacy/communication tradeoffs link to security."
|
||
autograd-computational-graphs:
|
||
primary: { vol: 1, chapter: frameworks }
|
||
also_see: [ { vol: 1, chapter: nn_computation } ]
|
||
why: "Static/dynamic graphs and reverse-mode autodiff are a frameworks topic."
|
||
software-portability:
|
||
primary: { vol: 1, chapter: frameworks }
|
||
also_see: [ { vol: 2, chapter: edge_intelligence } ]
|
||
why: "HAL/TVM/MLIR lowering is a frameworks topic; conversion bites hardest on edge."
|
||
sustainability-carbon-accounting:
|
||
primary: { vol: 2, chapter: sustainable_ai }
|
||
also_see: [ { vol: 1, chapter: responsible_engr } ]
|
||
why: "Operational vs embodied carbon is the sustainable-AI chapter's core."
|
||
differential-privacy:
|
||
primary: { vol: 2, chapter: security_privacy }
|
||
also_see: [ { vol: 1, chapter: responsible_engr } ]
|
||
why: "DP-SGD / epsilon budgets / privacy-utility live in security & privacy."
|
||
fairness-evaluation:
|
||
primary: { vol: 2, chapter: responsible_ai }
|
||
also_see: [ { vol: 1, chapter: responsible_engr } ]
|
||
why: "Demographic parity / equalized odds / subgroup eval is responsible-AI material."
|
||
responsible-ai:
|
||
primary: { vol: 2, chapter: responsible_ai }
|
||
also_see: [ { vol: 1, chapter: responsible_engr } ]
|
||
why: "Model cards, red-teaming, governance frameworks are the responsible-AI chapter."
|
||
tco-cost-modeling:
|
||
primary: { vol: 2, chapter: compute_infrastructure }
|
||
also_see: [ { vol: 2, chapter: ops_scale } ]
|
||
why: "Buy-vs-rent / spot-vs-reserved / cost-perf Pareto is fleet-infrastructure economics."
|
||
|
||
# ------------------------------------------------------------------------- data
|
||
data-pipeline-engineering:
|
||
primary: { vol: 1, chapter: data_engineering }
|
||
also_see: [ { vol: 2, chapter: data_storage } ]
|
||
why: "ETL/ELT, loaders, the data-pipeline equation are the data-engineering chapter."
|
||
feature-store-management:
|
||
primary: { vol: 1, chapter: data_engineering }
|
||
also_see: [ { vol: 2, chapter: data_storage } ]
|
||
why: "Online/offline stores and point-in-time correctness are introduced in data engineering."
|
||
data-quality-validation:
|
||
primary: { vol: 1, chapter: data_engineering }
|
||
why: "Schema validation, data contracts, quality gates are data-engineering fundamentals."
|
||
dataset-curation:
|
||
primary: { vol: 1, chapter: data_engineering }
|
||
also_see: [ { vol: 1, chapter: data_selection } ]
|
||
why: "Annotation workflows / IAA / dataset bias sit in data engineering; selection extends it."
|
||
streaming-ingestion:
|
||
primary: { vol: 1, chapter: data_engineering }
|
||
also_see: [ { vol: 2, chapter: data_storage } ]
|
||
why: "Stream processing and sensor ingestion are part of the data-engineering pipeline."
|
||
storage-format-selection:
|
||
primary: { vol: 2, chapter: data_storage }
|
||
also_see: [ { vol: 1, chapter: data_engineering } ]
|
||
why: "Parquet/TFRecord/columnar-vs-row and storage tiers are the data-storage chapter."
|
||
data-efficiency-selection:
|
||
primary: { vol: 1, chapter: data_selection }
|
||
also_see: [ { vol: 1, chapter: data_engineering } ]
|
||
why: "Coresets, curriculum, the data wall, ICR are exactly the data-selection chapter."
|
||
|
||
# ------------------------------------------------------------------- deployment
|
||
model-serving-infrastructure:
|
||
primary: { vol: 1, chapter: model_serving }
|
||
also_see: [ { vol: 2, chapter: inference } ]
|
||
why: "Inference servers, autoscaling, cold start are the model-serving chapter."
|
||
mlops-lifecycle:
|
||
primary: { vol: 1, chapter: ml_ops }
|
||
also_see: [ { vol: 2, chapter: ops_scale } ]
|
||
why: "Registries, CI/CD for ML, training-serving consistency are MLOps fundamentals."
|
||
ota-firmware-updates:
|
||
primary: { vol: 2, chapter: edge_intelligence }
|
||
also_see: [ { vol: 1, chapter: ml_ops } ]
|
||
why: "A/B partitions, FOTA, flash constraints are an edge/TinyML deployment topic."
|
||
container-orchestration:
|
||
primary: { vol: 2, chapter: fleet_orchestration }
|
||
also_see: [ { vol: 1, chapter: ml_ops } ]
|
||
why: "Kubernetes, GPU device plugins, job scheduling are fleet-orchestration material."
|
||
model-format-conversion:
|
||
primary: { vol: 2, chapter: edge_intelligence }
|
||
also_see: [ { vol: 1, chapter: frameworks } ]
|
||
why: "ONNX/TFLite/CoreML/TensorRT conversion and op-coverage gaps are edge concerns."
|
||
ab-rollout-strategies:
|
||
primary: { vol: 1, chapter: ml_ops }
|
||
also_see: [ { vol: 2, chapter: ops_scale } ]
|
||
why: "Blue-green/canary/shadow and progressive rollout are MLOps practices."
|
||
compound-ai-systems:
|
||
primary: { vol: 2, chapter: inference }
|
||
also_see: [ { vol: 1, chapter: model_serving } ]
|
||
why: "RAG, agent orchestration, chained-inference latency are an inference-systems topic."
|
||
disaggregated-serving:
|
||
primary: { vol: 2, chapter: inference }
|
||
also_see: [ { vol: 1, chapter: model_serving } ]
|
||
why: "Prefill/decode split and cross-node KV transfer are an advanced inference topic."
|
||
model-adaptation-systems:
|
||
primary: { vol: 2, chapter: inference }
|
||
also_see: [ { vol: 2, chapter: edge_intelligence } ]
|
||
why: "LoRA serving / personalized inference; on-device adaptation links to edge."
|
||
|
||
# ---------------------------------------------------------------------- latency
|
||
latency-decomposition:
|
||
primary: { vol: 1, chapter: model_serving }
|
||
also_see: [ { vol: 2, chapter: inference } ]
|
||
why: "End-to-end latency breakdown is taught with serving; TTFT/TPOT detailed at inference."
|
||
batching-strategies:
|
||
primary: { vol: 1, chapter: model_serving }
|
||
also_see: [ { vol: 2, chapter: inference } ]
|
||
why: "Static/dynamic/continuous batching is core to serving throughput."
|
||
tail-latency:
|
||
primary: { vol: 1, chapter: model_serving }
|
||
also_see: [ { vol: 2, chapter: ops_scale } ]
|
||
why: "P99/P999, hedged requests, SLA design are a serving topic; reinforced at fleet scale."
|
||
real-time-deadlines:
|
||
primary: { vol: 2, chapter: edge_intelligence }
|
||
also_see: [ { vol: 1, chapter: model_serving } ]
|
||
why: "Frame budgets, WCET, jank/ANR are edge/mobile real-time concerns."
|
||
profiling-bottleneck-analysis:
|
||
primary: { vol: 1, chapter: benchmarking }
|
||
also_see: [ { vol: 2, chapter: performance_engineering } ]
|
||
why: "Profilers, flame graphs, trace tools are introduced with benchmarking."
|
||
queueing-theory:
|
||
primary: { vol: 1, chapter: model_serving }
|
||
also_see: [ { vol: 2, chapter: performance_engineering } ]
|
||
why: "Little's Law and capacity sizing underpin serving; applied in perf engineering."
|
||
|
||
# ----------------------------------------------------------------------- memory
|
||
vram-budgeting:
|
||
primary: { vol: 1, chapter: training }
|
||
also_see: [ { vol: 2, chapter: inference } ]
|
||
why: "Weights+optimizer+activations accounting is a training-memory topic; KV-cache at inference."
|
||
kv-cache-management:
|
||
primary: { vol: 2, chapter: inference }
|
||
also_see: [ { vol: 1, chapter: model_serving } ]
|
||
why: "Paged attention, eviction, long-context pressure are inference-systems topics."
|
||
memory-hierarchy-design:
|
||
primary: { vol: 1, chapter: hw_acceleration }
|
||
also_see: [ { vol: 2, chapter: compute_infrastructure } ]
|
||
why: "Registers/SRAM/HBM/DRAM capacity-bandwidth-latency is a hardware topic."
|
||
activation-memory:
|
||
primary: { vol: 1, chapter: training }
|
||
also_see: [ { vol: 2, chapter: distributed_training } ]
|
||
why: "Gradient checkpointing and the compute-memory tradeoff are training-time concerns."
|
||
memory-mapped-inference:
|
||
primary: { vol: 2, chapter: edge_intelligence }
|
||
also_see: [ { vol: 1, chapter: model_serving } ]
|
||
why: "mmap weight loading and cold-start avoidance are mobile/edge serving techniques."
|
||
tensor-arena-planning:
|
||
primary: { vol: 2, chapter: edge_intelligence }
|
||
also_see: [ { vol: 1, chapter: model_compression } ]
|
||
why: "Flat tensor arenas and peak-SRAM scheduling are a TinyML topic."
|
||
dma-data-movement:
|
||
primary: { vol: 1, chapter: hw_acceleration }
|
||
also_see: [ { vol: 2, chapter: compute_infrastructure } ]
|
||
why: "DMA, zero-copy, pinned memory, host-device movement are hardware-level."
|
||
memory-pressure-management:
|
||
primary: { vol: 1, chapter: training }
|
||
also_see: [ { vol: 2, chapter: inference } ]
|
||
why: "OOM/fragmentation/gradient-accumulation are training-memory tactics; eviction at serving."
|
||
|
||
# ------------------------------------------------------------------- networking
|
||
collective-communication:
|
||
primary: { vol: 2, chapter: collective_communication }
|
||
why: "AllReduce/AllGather/ReduceScatter and ring-vs-tree are this chapter exactly."
|
||
interconnect-topology:
|
||
primary: { vol: 2, chapter: network_fabrics }
|
||
also_see: [ { vol: 2, chapter: compute_infrastructure } ]
|
||
why: "Fat-tree/torus/dragonfly and NVLink/IB are the network-fabrics chapter."
|
||
network-bandwidth-bottlenecks:
|
||
primary: { vol: 2, chapter: network_fabrics }
|
||
also_see: [ { vol: 2, chapter: distributed_training } ]
|
||
why: "Bisection bandwidth and comm-compute ratio are network-fabrics topics."
|
||
rdma-transport:
|
||
primary: { vol: 2, chapter: network_fabrics }
|
||
why: "RDMA/RoCE/IB verbs and kernel bypass are high-performance-transport material."
|
||
load-balancing:
|
||
primary: { vol: 1, chapter: model_serving }
|
||
also_see: [ { vol: 2, chapter: fleet_orchestration } ]
|
||
why: "Request routing / consistent hashing for inference traffic is a serving topic."
|
||
congestion-control:
|
||
primary: { vol: 2, chapter: network_fabrics }
|
||
why: "ECN/PFC/DCQCN and incast are GPU-cluster network-fabrics topics."
|
||
|
||
# ------------------------------------------------------------------ optimization
|
||
pruning-sparsity:
|
||
primary: { vol: 1, chapter: model_compression }
|
||
also_see: [ { vol: 2, chapter: performance_engineering } ]
|
||
why: "Structured/unstructured pruning and accelerator-aligned sparsity are compression."
|
||
knowledge-distillation:
|
||
primary: { vol: 1, chapter: model_compression }
|
||
why: "Teacher-student, logit/feature distillation are the model-compression chapter."
|
||
kernel-fusion:
|
||
primary: { vol: 2, chapter: performance_engineering }
|
||
also_see: [ { vol: 1, chapter: frameworks } ]
|
||
why: "Fusing memory-bound ops and launch-overhead reduction is a perf-engineering topic."
|
||
graph-compilation:
|
||
primary: { vol: 1, chapter: frameworks }
|
||
also_see: [ { vol: 2, chapter: performance_engineering } ]
|
||
why: "AOT compilation, operator lowering, constant folding are framework-compiler topics."
|
||
operator-scheduling:
|
||
primary: { vol: 2, chapter: performance_engineering }
|
||
also_see: [ { vol: 1, chapter: frameworks } ]
|
||
why: "Execution-order optimization for memory reuse is a perf-engineering topic."
|
||
flash-attention:
|
||
primary: { vol: 2, chapter: inference }
|
||
also_see: [ { vol: 2, chapter: performance_engineering } ]
|
||
why: "IO-aware tiling / online softmax is taught alongside attention inference."
|
||
speculative-decoding:
|
||
primary: { vol: 2, chapter: inference }
|
||
why: "Draft-verify decoding and acceptance rates are an autoregressive-inference topic."
|
||
|
||
# ------------------------------------------------------------------- parallelism
|
||
communication-computation-overlap:
|
||
primary: { vol: 2, chapter: distributed_training }
|
||
also_see: [ { vol: 2, chapter: collective_communication } ]
|
||
why: "Hiding collectives/DMA behind compute is a distributed-training scheduling topic."
|
||
data-parallelism:
|
||
primary: { vol: 2, chapter: distributed_training }
|
||
why: "Replicated training, gradient averaging, FSDP/ZeRO are distributed-training core."
|
||
model-tensor-parallelism:
|
||
primary: { vol: 2, chapter: distributed_training }
|
||
why: "Column/row partitioning across devices is distributed-training material."
|
||
pipeline-parallelism:
|
||
primary: { vol: 2, chapter: distributed_training }
|
||
why: "Stage splitting, micro-batching, bubble overhead are distributed-training topics."
|
||
3d-parallelism:
|
||
primary: { vol: 2, chapter: distributed_training }
|
||
why: "Combining DP+TP+PP for frontier training is the distributed-training chapter."
|
||
gradient-synchronization:
|
||
primary: { vol: 2, chapter: collective_communication }
|
||
also_see: [ { vol: 2, chapter: distributed_training } ]
|
||
why: "AllReduce variants, gradient compression, async SGD are collective-comm topics."
|
||
scheduling-resource-management:
|
||
primary: { vol: 2, chapter: fleet_orchestration }
|
||
also_see: [ { vol: 2, chapter: compute_infrastructure } ]
|
||
why: "MIG/MPS, gang scheduling, preemption, multi-tenancy are fleet-orchestration topics."
|
||
|
||
# ------------------------------------------------------------------------ power
|
||
power-budgeting:
|
||
primary: { vol: 2, chapter: sustainable_ai }
|
||
also_see: [ { vol: 1, chapter: hw_acceleration } ]
|
||
why: "TDP/DVFS/CMOS energy equation and energy-per-inference anchor the sustainability chapter."
|
||
thermal-management:
|
||
primary: { vol: 2, chapter: compute_infrastructure }
|
||
also_see: [ { vol: 2, chapter: sustainable_ai } ]
|
||
why: "Cooling and sustained-vs-burst throttling are datacenter-infrastructure topics."
|
||
energy-per-operation:
|
||
primary: { vol: 2, chapter: sustainable_ai }
|
||
also_see: [ { vol: 1, chapter: hw_acceleration } ]
|
||
why: "The Horowitz energy table and memory-vs-compute energy are sustainability core."
|
||
duty-cycling:
|
||
primary: { vol: 2, chapter: edge_intelligence }
|
||
also_see: [ { vol: 2, chapter: sustainable_ai } ]
|
||
why: "Sleep/wake, coin-cell budgets, harvesting are TinyML always-on topics."
|
||
datacenter-efficiency:
|
||
primary: { vol: 2, chapter: sustainable_ai }
|
||
also_see: [ { vol: 2, chapter: compute_infrastructure } ]
|
||
why: "PUE, rack power, carbon-aware scheduling are the sustainability chapter."
|
||
|
||
# -------------------------------------------------------------------- precision
|
||
quantization-fundamentals:
|
||
primary: { vol: 1, chapter: model_compression }
|
||
why: "INT8/INT4, zero-point, PTQ-vs-QAT, per-tensor-vs-per-channel are compression core."
|
||
mixed-precision-training:
|
||
primary: { vol: 1, chapter: training }
|
||
also_see: [ { vol: 1, chapter: model_compression } ]
|
||
why: "FP16/BF16/FP8, loss scaling, mixed-precision recipes are training-time topics."
|
||
extreme-quantization:
|
||
primary: { vol: 1, chapter: model_compression }
|
||
why: "Sub-4-bit, binary/ternary, GPTQ/AWQ are advanced model-compression topics."
|
||
|
||
# ------------------------------------------------------------------- reliability
|
||
fault-tolerance-checkpointing:
|
||
primary: { vol: 2, chapter: fault_tolerance }
|
||
also_see: [ { vol: 1, chapter: training } ]
|
||
why: "Checkpoint strategy, Young-Daly, preemption recovery are the fault-tolerance chapter."
|
||
distribution-drift-detection:
|
||
primary: { vol: 1, chapter: ml_ops }
|
||
also_see: [ { vol: 2, chapter: ops_scale } ]
|
||
why: "Data/concept drift and training-serving skew are MLOps monitoring topics."
|
||
graceful-degradation:
|
||
primary: { vol: 2, chapter: robust_ai }
|
||
also_see: [ { vol: 2, chapter: fault_tolerance } ]
|
||
why: "Degradation ladders, fallbacks, QoS shedding are a robust-AI topic."
|
||
safety-certification:
|
||
primary: { vol: 2, chapter: robust_ai }
|
||
also_see: [ { vol: 2, chapter: edge_intelligence } ]
|
||
why: "ISO 26262, watchdogs, deterministic execution are robustness/safety topics."
|
||
adversarial-robustness:
|
||
primary: { vol: 2, chapter: security_privacy }
|
||
also_see: [ { vol: 2, chapter: robust_ai } ]
|
||
why: "Adversarial attacks, prompt injection, model extraction are security topics."
|
||
monitoring-observability:
|
||
primary: { vol: 1, chapter: ml_ops }
|
||
also_see: [ { vol: 2, chapter: ops_scale } ]
|
||
why: "Telemetry, alerting, MTBF/MTTR are MLOps; scaled out in ops-at-scale."
|