docs: improve figure captions with bold titles and descriptions

Updated all mermaid diagram captions across the site to follow a consistent format:
- Bold title followed by a period
- Descriptive explanation of the diagram
- Ends with a period

Files updated:
- big-picture.md: TinyTorch Module Flow
- getting-started.md: TinyTorch Build Cycle
- milestones.md: Pedagogical Acts, Journey Through ML History
- intro.md: Build-Use-Reflect Learning Cycle
- learning-journey.md: Six-Act Learning Narrative
- optimization.md: Optimization Module Flow, Production Timeline
- foundation.md: Module Dependencies, Tier Milestones
- architecture.md: Module Flow, Tier Milestones
- modules.md: Module Development Workflow
- data.md: Progress Tracking Flow

🤖 Generated with [Claude Code](https://claude.com/claude-code)

tinytorch/site/big-picture.md

@@ -22,7 +22,7 @@ TinyTorch takes you from basic tensors to production-ready ML systems through 20
 
 ```{mermaid}
 :align: center
-:caption: TinyTorch Module Flow
+:caption: "**TinyTorch Module Flow.** The 20 modules progress through three tiers: Foundation (blue) builds core ML primitives, Architecture (purple) applies them to vision and language tasks, and Optimization (orange) makes systems production-ready."
 
 graph LR
     subgraph F["FOUNDATION (01-07)"]

tinytorch/site/chapters/learning-journey.md

@@ -11,7 +11,7 @@ TinyTorch's 20 modules follow a carefully crafted six-act narrative arc. Each ac
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**Six-Act Learning Narrative.** TinyTorch's 20 modules follow a carefully crafted arc from atomic components through production systems."
 graph LR
  Act1["Act I: Foundation<br/>01-04<br/>Atomic Components"] --> Act2["Act II: Learning<br/>05-07<br/>Gradient Revolution"]
  Act2 --> Act3["Act III: Data & Scale<br/>08-09<br/>Real Complexity"]

tinytorch/site/chapters/milestones.md

@@ -43,7 +43,7 @@ See [The Learning Journey](learning-journey.md) for the complete pedagogical nar
 
 ```{mermaid}
 :align: center
-:caption: Pedagogical Acts (What You're Learning)
+:caption: "**Pedagogical Acts and Historical Milestones.** Two dimensions of progress: Acts explain what you learn while milestones validate what you can build."
 graph TB
  subgraph "Pedagogical Acts (What You're Learning)"
  A1["Act I: Foundation<br/>Modules 01-04<br/>Atomic Components"]
@@ -100,7 +100,7 @@ graph TB
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**Journey Through ML History.** Six decades of breakthroughs you recreate with your own implementations, from the 1957 Perceptron to modern production systems."
 timeline
  title Journey Through ML History
  1957 : Perceptron : Binary classification with gradient descent

tinytorch/site/getting-started.md

@@ -86,7 +86,7 @@ TinyTorch follows a simple three-step workflow that you'll repeat for each modul
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**TinyTorch Build Cycle.** The three-step workflow you repeat for each module: edit in Jupyter, export to the package, and validate with milestone scripts."
 graph LR
  A[1. Edit Module<br/>modules/NN_name.ipynb] --> B[2. Export to Package<br/>tito module complete N]
  B --> C[3. Validate with Milestones<br/>Run milestone scripts]

tinytorch/site/intro.md

@@ -268,7 +268,7 @@ Every module follows a proven learning cycle that builds deep understanding:
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**Build-Use-Reflect Learning Cycle.** Every module follows this proven pattern: implement from scratch, apply to real problems, then answer systems thinking questions."
 graph LR
     B[Build<br/>Implement from scratch] --> U[Use<br/>Real data, real problems]
     U --> R[Reflect<br/>Systems thinking questions]

tinytorch/site/tiers/architecture.md

@@ -19,7 +19,7 @@ The Architecture tier teaches you how to build the neural network architectures
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**Architecture Module Flow.** Two parallel tracks branch from Foundation: vision (DataLoader, Convolutions) and language (Tokenization through Transformers)."
 graph TB
  F[ Foundation<br/>Tensor, Autograd, Training]
 
@@ -124,7 +124,7 @@ graph TB
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**Architecture Tier Milestones.** After completing modules 08-13, you unlock computer vision (1998 CNN) and language understanding (2017 Transformer) breakthroughs."
 timeline
  title Historical Achievements Unlocked
  1998 : CNN Revolution : 75%+ accuracy on CIFAR-10 with spatial intelligence

tinytorch/site/tiers/foundation.md

@@ -19,7 +19,7 @@ The Foundation tier teaches you how to build a complete learning system from scr
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**Foundation Module Dependencies.** Tensors and activations feed into layers, which connect to losses and autograd, enabling optimizers and ultimately training loops."
 graph TB
     M01[01. Tensor<br/>Multidimensional arrays] --> M03[03. Layers<br/>Linear transformations]
     M02[02. Activations<br/>Non-linear functions] --> M03
@@ -125,7 +125,7 @@ graph TB
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**Foundation Tier Milestones.** After completing modules 01-07, you unlock three historical achievements spanning three decades of neural network breakthroughs."
 timeline
     title Historical Achievements Unlocked
     1957 : Perceptron : Binary classification with gradient descent

tinytorch/site/tiers/optimization.md

@@ -19,7 +19,7 @@ The Optimization tier teaches you how to make ML systems fast, small, and deploy
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**Optimization Module Flow.** Starting from profiling, two parallel tracks address size reduction (quantization, compression) and speed improvement (memoization, acceleration), converging at benchmarking."
 graph TB
  A[️ Architecture<br/>CNNs + Transformers]
 
@@ -138,7 +138,7 @@ graph TB
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**Production Optimization Timeline.** Progressive improvements from baseline to production-ready: 8-16× smaller models and 12-40× faster inference."
 timeline
  title Production-Ready Systems
  Baseline : 100MB model, 0.5 tokens/sec, 95% accuracy

tinytorch/site/tito/data.md

@@ -13,7 +13,7 @@ TinyTorch uses a clean, simple approach to track your ML systems engineering jou
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**Progress Tracking Flow.** Build modules, export to package, unlock historical milestones, and track achievements through two parallel systems."
 graph LR
  A[Build Modules] --> B[Complete 01-20]
  B --> C[Export to Package]

tinytorch/site/tito/modules.md

@@ -13,7 +13,7 @@ TinyTorch follows a simple build-export-validate cycle:
 
 ```{mermaid}
 :align: center
-:caption: Architecture Overview
+:caption: "**Module Development Workflow.** The core cycle for building TinyTorch: start a module, edit in Jupyter, export to the package, test your imports, then move to the next module."
 graph LR
  A[Start/Resume Module] --> B[Edit in Jupyter]
  B --> C[Complete & Export]