{
  "docId": "019dd923-5e88-73ef-bd5c-fd5012384ae3",
  "docSlug": "bf350dd574c19997",
  "documentTitle": "2021 Air Street Capital The State of AI Report 2021",
  "authorId": "AirStreetCapital",
  "authorName": "Air Street Capital",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 60,
  "pageCount": 188,
  "prevPage": 59,
  "nextPage": 61,
  "slideType": "industry_trends",
  "function": "analyze_data",
  "density": "dense",
  "nDataPoints": 3,
  "notes": "The slide highlights the trade-off between dataset size and training efficiency, showcasing specific techniques like SEALS and SVP.",
  "elementsJson": [
    "headline_text",
    "paragraph",
    "bullet_list",
    "line_chart"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-fd5012384ae3/60",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3#slide-60",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Web-scale active learning on billions of examples is now possible with SEALS, which reduces the computational cost of data selection algorithms by 10-1000x.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d29-b987897f69be",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.35,
        "w": 0.45,
        "x": 0.52,
        "y": 0.42
      },
      "kind": "chart",
      "text": "Top-1 Test Error on CIFAR10 (%) vs Training Time in Hours on 1 P100 GPU",
      "attrs": null,
      "subkind": "line",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "c6d4d624-b9d9-4284-b4d2-ca9933d5809a",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.35,
        "w": 0.48,
        "x": 0.03,
        "y": 0.38
      },
      "kind": "list",
      "text": "Data selection methods improve the efficiency of AI/ML by identifying the most valuable points to label (active learning) or train on (core-set selection).\nWeb-scale active learning on billions of examples is now possible with SEALS, which reduces the computational cost of data selection algorithms by 10-1000x.\n50% of CIFAR10 can be removed without impacting accuracy using SVP, leading to a 1.6x speed-up in end-to-end training.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "7742bfd6-b450-4fbb-a12a-70a04a0557e6",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Top-1 Test Error: 1.6x",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d29-becafce49133",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.12,
        "w": 0.95,
        "x": 0.03,
        "y": 0.21
      },
      "kind": "paragraph",
      "text": "Working with massive datasets is cumbersome and expensive. Carefully selecting examples mitigates the pain of big data by focusing resources on the most valuable examples, but classical methods often become intractable at-scale. Recent approaches address these computational costs, enabling data selection on modern datasets.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "759c87c9-b74a-47ed-b49f-59d648d28ae3",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.8,
        "x": 0.03,
        "y": 0.14
      },
      "kind": "title",
      "text": "Careful data selection saves time and money by mitigating the pains of big data",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "6c1f12f5-6775-4f87-b2f4-224ddbe85a5d",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Chart Selection Guide",
      "slug": "chart-selection-guide",
      "agent": "Designer",
      "layer": "slide",
      "matchId": "d06f7858-4239-448d-81c7-96820dd49312",
      "evidence": "Chart/line: Top-1 Test Error on CIFAR10 (%) vs Training Time in Hours on 1 P100 GPU",
      "confidence": 0.6
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 152,
      "from": 5,
      "beatId": "019dd95a-0682-776c-8e35-0affbadec38e",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Definitions p.5-6, Exec Summary p.7, then Sections 1-3 catalog evidence.",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 152,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e35-1b3ee3a1c012",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Three sections accumulating evidence of accelerating progress.",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 63,
      "from": 56,
      "name": "Iceberg",
      "slug": "10-iceberg",
      "bestFor": "Consulting, complex problem solving, organizational change",
      "matchId": "019dd95a-07fe-70ce-8d3d-5f004461126b",
      "evidence": "Code availability, data cascades, dataset documentation, collusion rings, code+conferences.",
      "position": 8,
      "objective": "Diagnose openness and trust crisis in ML research",
      "structure": "The Symptom (Visible) -> The System (Hidden) -> The Root Cause",
      "confidence": 75,
      "description": "Reveal that the visible problem is merely a symptom of a deeper root cause"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}