{
  "kind": "framework",
  "value": "neural-network-architecture",
  "collectionKey": "slides:framework:neural-network-architecture:all-document-kinds:all-producers:all-orientations",
  "filters": {
    "documentKinds": [],
    "sourceTypes": [],
    "orientations": []
  },
  "total": 5,
  "page": 1,
  "pageSize": 24,
  "pageCount": 1,
  "rows": [
    {
      "docId": "019dd923-5de0-76bd-a168-6159b949e2c2",
      "docSlug": "ff5d549e5027972a",
      "documentTitle": "GPT-3 and the actuarial landscape",
      "authorId": "OliverWyman",
      "authorName": "Oliver Wyman",
      "documentKindSlug": "consulting-deck",
      "documentKindLabel": "Consulting deck",
      "sourceTypeSlug": "strategy_consulting",
      "sourceTypeLabel": "Strategy consulting",
      "presentationDate": null,
      "orientation": "landscape",
      "aspectRatio": 1.778,
      "pageNumber": 21,
      "slideType": "other",
      "function": "present_framework",
      "notes": "The slide illustrates a standard feed-forward neural network with an input layer, two hidden layers, and an output layer, specifically applied to the Iris dataset classification problem.",
      "imagePath": null,
      "matchCount": 1,
      "evidence": "Diagram of layers and nodes",
      "slideHref": "/slides/019dd923-5de0-76bd-a168-6159b949e2c2/21",
      "deckHref": "/decks/019dd923-5de0-76bd-a168-6159b949e2c2",
      "deckAnchorHref": "/decks/019dd923-5de0-76bd-a168-6159b949e2c2#slide-21",
      "loopMatches": [
        {
          "to": 25,
          "from": 17,
          "name": "Mece Breakdown",
          "slug": "40-mece-breakdown",
          "bestFor": "Problem structuring, ensuring completeness, strategic analysis",
          "matchId": "5fc4f6a3-76b0-4e01-8746-40ac791c194d",
          "evidence": "The deck provides a detailed breakdown of GPT-3's capabilities and applications in the actuarial field.",
          "position": 1,
          "objective": "How can GPT-3 be applied to actuarial work?",
          "structure": "The Whole -> Category A (distinct) -> Category B (distinct) -> Category C (distinct) -> Complete Coverage",
          "confidence": 0.6,
          "description": "Divide a complex topic into mutually exclusive, collectively exhaustive categories"
        }
      ],
      "arcBeatMatches": [
        {
          "to": 31,
          "from": 17,
          "beatId": "5259c9cc-c0ba-4428-ac14-7a6ba8d02be1",
          "arcName": "The Sparkline",
          "arcSlug": "sparkline",
          "beatName": "What Could Be",
          "beatSlug": "sparkline-what-could-be-2",
          "evidence": "The deck explores the potential applications of GPT-3 in the actuarial field.",
          "position": 2,
          "confidence": 0.8,
          "parentBeatName": "Turn",
          "parentBeatSlug": "turn"
        }
      ],
      "imagePathAlt": null,
      "thumbSrc": null,
      "thumbSrcAlt": null,
      "locked": true
    },
    {
      "docId": "019de06f-bf94-77b4-8bc1-619fd91f6e9b",
      "docSlug": "a7905d211e9881ccf329f81a7661699c",
      "documentTitle": "OpenAI | Product Presentation Deck | 52 slides",
      "authorId": "openai",
      "authorName": "OpenAI",
      "documentKindSlug": "conference-presentation",
      "documentKindLabel": "Conference presentation",
      "sourceTypeSlug": "investor_relations",
      "sourceTypeLabel": "Investor relations",
      "presentationDate": "2018-11-01 00:00:00",
      "orientation": "landscape",
      "aspectRatio": 1.7761332,
      "pageNumber": 17,
      "slideType": "other",
      "function": "present_framework",
      "notes": "The diagram depicts a neural network architecture involving convolutional layers (CONV) and a recurrent layer (LSTM) for robotic manipulation.",
      "imagePath": null,
      "matchCount": 1,
      "evidence": "Visual representation of CONV and LSTM layers processing sensor data",
      "slideHref": "/slides/019de06f-bf94-77b4-8bc1-619fd91f6e9b/17",
      "deckHref": "/decks/019de06f-bf94-77b4-8bc1-619fd91f6e9b",
      "deckAnchorHref": "/decks/019de06f-bf94-77b4-8bc1-619fd91f6e9b#slide-17",
      "loopMatches": [],
      "arcBeatMatches": [],
      "imagePathAlt": null,
      "thumbSrc": null,
      "thumbSrcAlt": null,
      "locked": true
    },
    {
      "docId": "019de06f-b8a3-7331-8935-2a15d6d59d93",
      "docSlug": "041e12e95b005675c8303cd029ca09ef",
      "documentTitle": "OpenAI | Product Presentation Deck | 64 slides",
      "authorId": "openai",
      "authorName": "OpenAI",
      "documentKindSlug": "conference-presentation",
      "documentKindLabel": "Conference presentation",
      "sourceTypeSlug": "investor_relations",
      "sourceTypeLabel": "Investor relations",
      "presentationDate": "2018-09-01 00:00:00",
      "orientation": "landscape",
      "aspectRatio": 1.7777778,
      "pageNumber": 33,
      "slideType": "other",
      "function": "present_framework",
      "notes": "The diagram represents a deep learning architecture for multi-camera vision processing.",
      "imagePath": null,
      "matchCount": 1,
      "evidence": "The slide depicts a standard deep learning pipeline structure.",
      "slideHref": "/slides/019de06f-b8a3-7331-8935-2a15d6d59d93/33",
      "deckHref": "/decks/019de06f-b8a3-7331-8935-2a15d6d59d93",
      "deckAnchorHref": "/decks/019de06f-b8a3-7331-8935-2a15d6d59d93#slide-33",
      "loopMatches": [],
      "arcBeatMatches": [],
      "imagePathAlt": null,
      "thumbSrc": null,
      "thumbSrcAlt": null,
      "locked": true
    },
    {
      "docId": "019de06f-b8a3-7331-8935-2a15d6d59d93",
      "docSlug": "041e12e95b005675c8303cd029ca09ef",
      "documentTitle": "OpenAI | Product Presentation Deck | 64 slides",
      "authorId": "openai",
      "authorName": "OpenAI",
      "documentKindSlug": "conference-presentation",
      "documentKindLabel": "Conference presentation",
      "sourceTypeSlug": "investor_relations",
      "sourceTypeLabel": "Investor relations",
      "presentationDate": "2018-09-01 00:00:00",
      "orientation": "landscape",
      "aspectRatio": 1.7777778,
      "pageNumber": 34,
      "slideType": "other",
      "function": "present_framework",
      "notes": "The diagram represents a standard deep reinforcement learning policy architecture.",
      "imagePath": null,
      "matchCount": 1,
      "evidence": "The slide depicts a sequential processing pipeline typical of neural network policy models.",
      "slideHref": "/slides/019de06f-b8a3-7331-8935-2a15d6d59d93/34",
      "deckHref": "/decks/019de06f-b8a3-7331-8935-2a15d6d59d93",
      "deckAnchorHref": "/decks/019de06f-b8a3-7331-8935-2a15d6d59d93#slide-34",
      "loopMatches": [],
      "arcBeatMatches": [],
      "imagePathAlt": null,
      "thumbSrc": null,
      "thumbSrcAlt": null,
      "locked": true
    },
    {
      "docId": "019dd923-605c-759f-b6b1-2c320370f5e4",
      "docSlug": "bi-aa755234ca05917f",
      "documentTitle": "The pitch deck FLYR Labs used to raise $150 million from investors",
      "authorId": "Pitchdecks",
      "authorName": "FLYR Labs",
      "documentKindSlug": "pitchdeck",
      "documentKindLabel": "Pitch deck",
      "sourceTypeSlug": "strategy_consulting",
      "sourceTypeLabel": "Strategy consulting",
      "presentationDate": null,
      "orientation": "landscape",
      "aspectRatio": 1.777,
      "pageNumber": 8,
      "slideType": "solution",
      "function": "present_solution",
      "notes": "The diagram illustrates a multi-layer perceptron or neural network structure mapping inputs to specific business outcomes.",
      "imagePath": null,
      "matchCount": 1,
      "evidence": "Visual representation of nodes and connections representing deep learning layers",
      "slideHref": "/slides/019dd923-605c-759f-b6b1-2c320370f5e4/8",
      "deckHref": "/decks/019dd923-605c-759f-b6b1-2c320370f5e4",
      "deckAnchorHref": "/decks/019dd923-605c-759f-b6b1-2c320370f5e4#slide-8",
      "loopMatches": [],
      "arcBeatMatches": [
        {
          "to": 9,
          "from": 5,
          "beatId": "94eb3e38-140c-4f1c-8c33-3b051409f197",
          "arcName": "The Sequoia Pitch",
          "arcSlug": "sequoia-pitch",
          "beatName": "Solution",
          "beatSlug": "sequoia-pitch-solution",
          "evidence": "The solution is presented on pages 5-9, highlighting the Cirrus Platform Capabilities and Using Deep Learning to Unlock Hidden Understanding",
          "position": 1,
          "confidence": 0.8,
          "parentBeatName": "Turn",
          "parentBeatSlug": "turn"
        }
      ],
      "imagePathAlt": null,
      "thumbSrc": null,
      "thumbSrcAlt": null,
      "locked": true
    }
  ]
}