{
  "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": 14,
  "pageCount": 188,
  "prevPage": 13,
  "nextPage": 15,
  "slideType": "industry_trends",
  "function": "summarize",
  "density": "dense",
  "nDataPoints": 2,
  "notes": "The slide uses two line charts to show the reduction in Word Error Rate (WER) over time for speech recognition and visual examples of 3D point cloud tasks.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "line_chart",
    "infographic"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-fd5012384ae3/14",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3#slide-14",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Self-attention is the basic building block of SOTA models on speech recognition... and on 3D point cloud classification.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d28-8537e3c597b3",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.35,
        "x": 0.61,
        "y": 0.285
      },
      "kind": "chart",
      "text": "WER reduction over time for test-clean and test-other datasets",
      "attrs": null,
      "subkind": "line",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "a258d72a-05d5-41cb-8616-a316f35e883c",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.32,
        "w": 0.28,
        "x": 0.68,
        "y": 0.58
      },
      "kind": "image",
      "text": "Visual examples of Point Transformer applications in 3D classification and segmentation",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "3173690a-dc78-4fa2-bf73-4b0e952fa376",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.35,
        "w": 0.65,
        "x": 0.03,
        "y": 0.52
      },
      "kind": "list",
      "text": "... and on 3D point cloud classification. A team from Oxford, CUHK and Intel Labs designed self-attention networks for point clouds named Point Transformers. Point Transformers significantly outperform prior work on diverse tasks such as object classification, object part segmentation, and semantic scene segmentation. e.g. They achieve a record 70.4% mIoU on S3DIS Area 5 for scene segmentation, surpassing the previous best by 3.3 percentage points.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "312a01c8-737c-46ba-bc7a-0b80e5f337c3",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.55,
        "x": 0.03,
        "y": 0.22
      },
      "kind": "list",
      "text": "Self-attention is the basic building block of SOTA models on speech recognition... The Conformer model combines self-attention and convolutions to capture both global interactions and local features. Giant Conformers pre-trained using wav2vec 2.0 and self-training achieve the lowest word-error rates (WER) to date on Librispeech.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "dd436a4c-9fe5-4132-a828-690e5ed5f6b8",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Word Error Rate (WER): 70.4%",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d28-8bc64ab07c69",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.85,
        "x": 0.03,
        "y": 0.13
      },
      "kind": "title",
      "text": "Transformers take over other major AI applications, e.g. audio and 3D point clouds",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "fcba9635-b64b-4f93-8180-5081daf677c3",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Action Titles",
      "slug": "action-titles",
      "agent": "Architect",
      "layer": "slide",
      "matchId": "019dd95a-0fd5-7148-8ed0-cfc7ec62898f",
      "evidence": "Title states transformers extending to audio + 3D.",
      "confidence": 78
    }
  ],
  "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": 18,
      "from": 11,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3d-45052222b756",
      "evidence": "Multiple evidence slides (vision, audio, 3D, MLPs comeback) all converging on transformer dominance.",
      "position": 2,
      "objective": "Show transformers spreading across AI domains",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 82,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}