{
  "nbformat": 4,
  "nbformat_minor": 5,
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "name": "python",
      "version": "3.11"
    },
    "colab": {
      "name": "week-18-exercise.ipynb"
    },
    "course_exercise": {
      "id": "W18",
      "week": "18",
      "hour": null,
      "date": "2027-01-04",
      "title": "Optional final written and oral rehearsal",
      "minutes": 20,
      "optional": true,
      "worksheet": "notes/exercises/week-18-exercise.html",
      "notebook": "notebooks/exercises/week-18-exercise.ipynb",
      "colab": "https://colab.research.google.com/github/CHjonnyYu/MLES-Fall-2026/blob/main/notebooks/exercises/week-18-exercise.ipynb",
      "guided_notebook": "notebooks/week-18-practice.ipynb",
      "execution_status": "New exercise extension not executed in this authoring run"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "# W18 Exercise: Optional final written and oral rehearsal\n\nMachine Learning in Engineering Science | NCKU / LAiMM | Fall 2026\n\n**Date:** 2027-01-04. **Exercise time:** 20 minutes within the class/practice allocation, not extra time after class.\n\n**Optional examination rehearsal. This is not the examination itself.**\n\n## How to work independently\n1. In Colab, save a copy to your Drive and use a CPU runtime. In Jupyter, open this notebook and select a Python kernel.\n2. Run the complete worked walkthrough below from top to bottom. Read every Markdown checkpoint; the walkthrough is included so no previous notebook state is needed.\n3. At the Independent Exercise section, write each prediction in the response cell before running its experiment.\n4. Run the starter experiment, make the requested controlled change, and record the actual result. Edit only the declared factor; preserve split rules and preprocessing.\n5. Explain one mechanism and one limitation. Export the evidence JSON and discuss it with a partner.\n\nThe core exercises need no paid API, private dataset, or GPU. The agent units use clearly labeled offline simulators, not real LLM calls.\n\n**Reproducibility boundary:** the original guided notebooks were previously executed; the new extension cells have not yet been execution-tested in this revision. Report unexpected behavior rather than claiming a check passed.\n"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "# Week 18: Final written and oral examination readiness\n\nMachine Learning in Engineering Science | NCKU + LAiMM | Fall 2026\n\n**Purpose:** a fully worked, self-paced in-class practice with an optional extension. Weeks 11 and 18 are optional examination-readiness materials. These notebooks do not create weekly graded assignments.\n\n**Before running:** choose a Python 3 kernel in Jupyter or a CPU runtime in Colab. Run every cell from top to bottom with Shift+Enter. Setup installs missing free packages. No API key or external dataset download is required.\n\n**Learning target:** complete the calculation, inspect intermediate values, and explain why the protocol supports a limited claim.\n\n**Time:** about 25-45 minutes including reading, prediction, execution, and explain-back.\n",
      "id": "cell-000"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "## 1. Set up and record the environment\n\nKeep the seed fixed for the first run. Record actual outputs and package versions rather than copying a claimed performance number.\n",
      "id": "cell-001"
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "outputs": [],
      "metadata": {},
      "source": "import sys, subprocess, importlib.util, platform, json, random, hashlib\nfrom pathlib import Path\nrequired = {\"numpy\": \"numpy\", \"matplotlib\": \"matplotlib\", \"sklearn\": \"scikit-learn\"}\nmissing = [package for module, package in required.items() if importlib.util.find_spec(module) is None]\nif missing:\n    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", *missing])\nimport numpy as np\nimport matplotlib.pyplot as plt\nSEED = 2026\nrandom.seed(SEED)\nnp.random.seed(SEED)\nrng = np.random.default_rng(SEED)\nARTIFACTS = Path(\"artifacts\")\nARTIFACTS.mkdir(exist_ok=True)\nprint(\"Python:\", platform.python_version(), \"NumPy:\", np.__version__, \"Seed:\", SEED)\n",
      "id": "cell-002"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "**Checkpoint.** The environment cell must finish before any analysis cell. Restart and run all if a variable is missing.\n",
      "id": "cell-003"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "## 2. Reconstruct the attention calculation\n\nSolve before running: scores [1,0,1]/sqrt(2), values [[10,0],[0,10],[10,10]].\n",
      "id": "cell-004"
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "outputs": [],
      "metadata": {},
      "source": "scores=np.array([1.,0.,1.])/np.sqrt(2)\nweights=np.exp(scores-scores.max()); weights/=weights.sum()\nvalues=np.array([[10.,0.],[0.,10.],[10.,10.]])\ncontext=weights@values\nprint(\"Weights:\",weights,\"Context:\",context)\nassert np.isclose(weights.sum(),1)\n",
      "id": "cell-005"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "**Checkpoint.** You should explain scores, softmax, and weighted retrieval as three distinct operations.\n",
      "id": "cell-006"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "## 3. Distinguish a model from an agent\n\nSort components by their role. This small schema is a rehearsal aid, not a grading rubric.\n",
      "id": "cell-007"
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "outputs": [],
      "metadata": {},
      "source": "components={\"predictor\":\"maps input tokens to next-token logits\",\n            \"tool\":\"executes a validated operation\",\n            \"controller\":\"chooses or validates the next bounded step\",\n            \"evidence\":\"records inputs, outputs, configuration and checks\",\n            \"human\":\"authorizes consequential actions and judges limits\"}\nfor name,role in components.items(): print(name+\": \"+role)\n",
      "id": "cell-008"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "**Checkpoint.** A Transformer supplies a model component; it does not by itself define permissions or an execution loop.\n",
      "id": "cell-009"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "## 4. Summarize a defensible explanation\n\nConnect reproducibility, interpretability, and uncertainty. No grade or project-performance claim is produced by this notebook.\n",
      "id": "cell-010"
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "outputs": [],
      "metadata": {},
      "source": "summary={\"attention_context\":context.tolist(),\"components\":components,\n         \"reproducibility\":\"same data, code, configuration and environment record\",\n         \"interpretability\":\"explain the computation and test selected interventions\",\n         \"limit\":\"attention weights alone do not prove causation\"}\nprint(json.dumps(summary,indent=2))\n",
      "id": "cell-011"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "**Checkpoint.** Use these questions to rehearse both the written and oral exam; exam policy remains the course assessment policy.\n",
      "id": "cell-012"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "## 6. Preserve your evidence\n\nExport a JSON record with a seed, package version, and measured result. Download the artifacts directory before leaving Colab; runtime storage is temporary.\n",
      "id": "cell-013"
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "outputs": [],
      "metadata": {},
      "source": "record={\"week\":18,\"seed\":SEED,\"numpy\":np.__version__,\"python\":platform.python_version(),\"result\":summary}\n(ARTIFACTS/\"week-18-evidence.json\").write_text(json.dumps(record,indent=2))\nprint(json.dumps(record,indent=2))\n",
      "id": "cell-014"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "**Checkpoint.** The evidence file must match the result you actually obtained. A saved screenshot alone does not permit rerunning the calculation.\n",
      "id": "cell-015"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "## 7. Try one change and explain it\n1. Predict the effect of one change before editing code. Change one parameter, input, or boundary condition only.\n2. Rerun all cells in a fresh kernel. Keep the original evidence record and compare the observed difference.\n3. Explain the result using the mechanism, not just the final number.\n4. Name one assumption that limits the claim, and a new test that could challenge it.\n\n**Troubleshooting:** if installation fails, restore network access; if a variable is undefined, run earlier cells; if your output differs, compare package versions, seed, and data construction. Do not repeatedly edit code until a preferred score appears.\n\n**Completion criterion:** one executed notebook, one evidence JSON, and a brief claim/evidence/limitation statement.\n\n### Reference documentation\n- [NumPy user guide](https://numpy.org/doc/stable/user/)\n- [scikit-learn user guide](https://scikit-learn.org/stable/user_guide.html)\n- [Course repository](https://github.com/CHjonnyYu/MLES-Fall-2026)\n",
      "id": "cell-016"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "## Independent Exercise: W18\n\nComplete the three tasks below after the walkthrough. The starter cells produce observations, not your written interpretation. Fill the response fields in the next cell. Save separate records for the original run and any controlled change."
    },
    {
      "cell_type": "code",
      "metadata": {},
      "execution_count": null,
      "outputs": [],
      "source": "exercise_id=\"W18\"\nobservations={}\nresponses={\n    'task1_prediction':'', 'task1_explanation':'',\n    'task2_prediction':'', 'task2_explanation':'',\n    'task3_prediction':'', 'task3_explanation':'',\n    'controlled_change':'', 'limitation':'', 'ai_use_and_checks':''\n}\n# Fill these strings before and after each experiment. Use 'none' if no AI assistance was used.\nprint('Exercise record initialized:', exercise_id)"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "### Task 1: Reconstruct the full attention operation\n\nPredict scores, weights, and context before running. Explain why a key with raw score zero can still receive positive weight.\n\n**Steps**\n1. Write your prediction in `responses['task1_prediction']` before running.\n2. Run the starter cell; read every printed quantity and retain the observation.\n3. Make the controlled comparison requested above. Record its configuration in `responses['controlled_change']`.\n4. Write a mechanism-based explanation in `responses['task1_explanation']`; do not merely repeat a score.\n\n**Checkpoint:** The context is about [8.0222,5.9889]. Scores, normalized weights, and retrieved values are distinct objects."
    },
    {
      "cell_type": "code",
      "metadata": {},
      "execution_count": null,
      "outputs": [],
      "source": "s_final=np.array([1.,0.,1.])/np.sqrt(2)\nw_final=np.exp(s_final-s_final.max()); w_final/=w_final.sum()\nv_final=np.array([[10.,0.],[0.,10.],[10.,10.]])\nobservations['task1']={'scores':s_final.tolist(),'weights':w_final.tolist(),'context':(w_final@v_final).tolist()}\nprint(observations['task1'])"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "### Task 2: Explain a causal mask\n\nBuild a four-position causal mask. Explain which positions the final query may use and which positions the first query cannot use.\n\n**Steps**\n1. Write your prediction in `responses['task2_prediction']` before running.\n2. Run the starter cell; read every printed quantity and retain the observation.\n3. Make the controlled comparison requested above. Record its configuration in `responses['controlled_change']`.\n4. Write a mechanism-based explanation in `responses['task2_explanation']`; do not merely repeat a score.\n\n**Checkpoint:** The first query can use only position 0; the last can use positions 0 through 3. These are illustrative weights, not a learned attention map."
    },
    {
      "cell_type": "code",
      "metadata": {},
      "execution_count": null,
      "outputs": [],
      "source": "mask_final=np.tril(np.ones((4,4),dtype=bool))\nweights_final=mask_final.astype(float)/mask_final.sum(axis=-1,keepdims=True)\nobservations['task2']={'allowed':mask_final.tolist(),'illustrative_uniform_weights':weights_final.tolist(),'row_sums':weights_final.sum(axis=-1).tolist()}\nprint(observations['task2'])"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "### Task 3: Defend a model versus an agent\n\nExplain the roles of model, validator, tool, state, and stopping rule. Name one action that must require human approval.\n\n**Steps**\n1. Write your prediction in `responses['task3_prediction']` before running.\n2. Run the starter cell; read every printed quantity and retain the observation.\n3. Make the controlled comparison requested above. Record its configuration in `responses['controlled_change']`.\n4. Write a mechanism-based explanation in `responses['task3_explanation']`; do not merely repeat a score.\n\n**Checkpoint:** A Transformer is a model component, not a complete permissioned agent. This practice does not change written/oral exam policy."
    },
    {
      "cell_type": "code",
      "metadata": {},
      "execution_count": null,
      "outputs": [],
      "source": "observations['task3']={'components':['predictor','validator','permitted tool','state','step budget','human oversight'],'exercise_type':'optional examination rehearsal'}\nprint(observations['task3'])"
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": "### Finish: preserve and explain\n\nFill all response strings, then run the export cell. A draft file is intentionally labeled incomplete; a complete response record is not automatically a scientifically correct result. Download the JSON before the Colab session ends. Share it with a partner for explain-back, not as an additional weekly submission.\n\n**Exit questions:** What changed? Which observation supports your explanation? What does this experiment not establish?"
    },
    {
      "cell_type": "code",
      "metadata": {},
      "execution_count": null,
      "outputs": [],
      "source": "missing_responses=[key for key,value in responses.items() if not str(value).strip()]\nexercise_record={'exercise':exercise_id,'status':'draft' if missing_responses else 'ready for peer discussion','responses':responses,'observations':observations,'missing_responses':missing_responses,'environment':{'python':platform.python_version(),'numpy':np.__version__},'data_scope':'course-provided or synthetic teaching data'}\nexercise_folder=Path('artifacts')/'exercises'; exercise_folder.mkdir(parents=True,exist_ok=True)\nexercise_path=exercise_folder/(exercise_id+'-evidence.json')\nexercise_path.write_text(json.dumps(exercise_record,indent=2,default=lambda value:value.tolist() if hasattr(value,'tolist') else str(value)))\nprint('Saved:',exercise_path)\nprint('Status:',exercise_record['status'])\nprint('Fields still to complete:',missing_responses)"
    }
  ]
}