pop-your-filter-bubble.pdf

Transcript

1. 1.

   1 Pop Your Filter Bubble

2. 2.

   2 ML and Me Dinesh Vadhia Systems background ML 10+

   years Python, Numpy and Scipy since 2007 Collaboration with Professor Zoubin Ghahramani at Cambridge University www.xyggy.com © 2019
3. 3.

   3 1. Bubble 2. Your filter 3. Pop www.xyggy.com ©

   2019
4. 4.

   4 Bubble 2016 Brexit referendum and US election a turning

   point Bad stuff happened and continues to happen Social media and recommendation engines implicated www.xyggy.com © 2019
5. 5.

   5 The worm has turned Up Next: A Better Recommendation

   System, Renne Diresta, Wired, April ‘18 We are all trapped in the “Feed”, Om Malik, May ’18 The Expensive Education of Mark Zuckerberg and Silicon Valley, Kara Swisher, New York Times, Aug ‘18 www.xyggy.com © 2019
6. 6.

   6 Francois Chollet asks … Is “super intelligence” the real

   danger or … … the scalable manipulation of human behavior AI enables, … and its malicious use by corporations and governments? What worries me about AI Francois Chollet, creator of Keras, neural networks library Medium, Mar ‘18 www.xyggy.com © 2019
7. 7.

   7 www.xyggy.com © 2019 Villain is the ScreenSlayer It takes

   over people’s mind and agency
8. 8.

   8 1. Bubble 2. Your filter 3. Pop www.xyggy.com ©

   2019
9. 9.

   9 AI has all the control Recommendation engines have spread

   like a virus because open source makes it easy … All behave the same, with each consumer … … in a single lane without control … not an open road with control www.xyggy.com © 2019
10. 10.

    10 Static AI in the enterprise Built over decades, integrated

    enterprise workflows are dynamic AI is static Caveat emptor www.xyggy.com © 2019
11. 11.

    11 Learning algorithms Invented by academics for experimental research (50’s

    to 90’s). Not designed for: i. Real-world use (not dynamic) ii. Interactivity (no control) iii. Scalability (in production) www.xyggy.com © 2019
12. 12.

    12 Machine learning pipeline machine learning model data feature engineering

    unseen data train test deploy production offline www.xyggy.com © 2019 manual or deep learning predictions
13. 13.

    13 Static machine leaning machine learning static model new data

    feature engineering unseen data retrain retest redeploy www.xyggy.com © 2019 production offline predictions
14. 14.

    14 Dynamic machine learning www.xyggy.com © 2019 predictions production data

    feature engineering dynamic machine learning unseen data
15. 15.

    15 1. Bubble 2. Your filter 3. Pop www.xyggy.com ©

    2019
16. 16.

    16 data: add update delete read query: standard more like

    this/these more or less anomaly detection dynamic automatic generalization interactive Thingy A P I A P I Thingy is a dynamic recommendation engine www.xyggy.com © 2019
17. 17.

    17 www.xyggy.com © 2019 Thingy query of things things results

    ranked by how well each thing “fits into” universe of things including the query
18. 18.

    18 query www.xyggy.com © 2019

19. 19.

    19 Query images Result images Query Dataset: wikiart images -

    https://www.wikiart.org/. No image pre-processing performed. No textual data used. Feature vectors generated automatically with deep learning. www.xyggy.com © 2019
20. 20.

    20 Add 2nd image to query www.xyggy.com © 2019 Query

    images Result images
21. 21.

    21 www.xyggy.com © 2019 Add 3rd image to query Query

    images Result images
22. 22.

    22 Add 4th image to query www.xyggy.com © 2019 Query

    images Result images
23. 23.

    23 query: add & remove www.xyggy.com © 2019

24. 24.

    24 Add and remove images Query images Result images Dataset:

    wikiart images - https://www.wikiart.org/. No image pre-processing performed. No textual data used. Feature vectors generated automatically with deep learning. www.xyggy.com © 2019
25. 25.

    25 Add 2nd image to query www.xyggy.com © 2019 Query

    images Result images
26. 26.

    26 Add two more images to query www.xyggy.com © 2019

    Query images Result images
27. 27.

    27 Remove two images from query www.xyggy.com © 2019 Query

    images Result images
28. 28.

    28 API www.xyggy.com © 2019

29. 29.

    29 API v0.3: Request / Response www.xyggy.com © 2019 import

    json, requests url = ‘http://127.0.0.1:8181’ + ‘/thingy/api/v0.3’ headers = {‘content-type’:’application/json’} data = json.dumps(payload) response = requests.post(url, headers, data) results = response.json()
30. 30.

    30 API: query www.xyggy.com © 2019 # query request_type =

    query|query_more|query_pos|query_neg # detect query request_type = detect # crud request_type = crud_add|crud_read|crud_update|crud_delete request_type = “query” number_of_results = 10 include_scores = True payload = { 'meta': {'request_type':request_type, 'number_of_results':number_of_results, 'include_scores': include_scores}, 'unknown_items': unknown_items, 'known_items': known_items}
31. 31.

    31 query: more like this/these www.xyggy.com © 2019

32. 32.

    32 More like this Query images Result images Dataset: 110K

    Visual Genome images - http://visualgenome.org/ No image pre-processing performed. No textual data used. Feature vectors generated automatically with deep learning. www.xyggy.com © 2019
33. 33.

    33 More like this www.xyggy.com © 2019 Query images Result

    images
34. 34.

    34 More like these Query images Result images www.xyggy.com ©

    2019
35. 35.

    35 More like these www.xyggy.com © 2019 Query images Result

    images
36. 36.

    36 query: more like these, less like others www.xyggy.com ©

    2019
37. 37.

    37 More like these, less like others Query images Result

    images Dataset: wikiart images - https://www.wikiart.org/. No image pre-processing performed. No textual data used. Feature vectors generated automatically with deep learning. www.xyggy.com © 2019
38. 38.

    38 More like +’s, less like –’s www.xyggy.com © 2019

    Query images Query images
39. 39.

    39 More like +’s, less like –’s www.xyggy.com © 2019

    Result images
40. 40.

    40 More like –’s, less like +’s www.xyggy.com © 2019

    Query images Query images
41. 41.

    41 More like –’s, less like +’s www.xyggy.com © 2019

    Result images
42. 42.

    42 Yin and Yang www.xyggy.com © 2019

43. 43.

    43 crud: add data www.xyggy.com © 2019

44. 44.

    44 Litmus test to add unknown image 1. Query with

    an unknown image. If image is known to Thingy, duplicate will show as the first result. It doesn’t (next slide). 2. Add a copy of the unknown image to Thingy. 3. Query with the unknown image again. If image is known to Thingy, duplicate will show as the first result. www.xyggy.com © 2019
45. 45.

    45 1. Query with unknown image Dataset: wikiart images -

    https://www.wikiart.org/. No image pre-processing performed. No textual data used. Feature vectors generated automatically from deep learning model. Unknown image U U not in Thingy www.xyggy.com © 2019
46. 46.

    46 2. Add image Add a copy of unknown image

    U to Thingy in realtime www.xyggy.com © 2019
47. 47.

    47 3. Query with unknown image again Unknown image U

    Copy of U is first result www.xyggy.com © 2019
48. 48.

    48 Test to add 3 unknown images 1. Query with

    3 unknown images. If images are known, duplicates will show in results. They don’t (see next slide). 2. Add copies of 3 unknown images to Thingy. 3. Query with 3 unknown images again. If images are known, duplicates will show in results. www.xyggy.com © 2019
49. 49.

    49 1. Query with 3 unknown images Unknown images U1,

    U2, U3 U1, U2, U3 not in Thingy www.xyggy.com © 2019
50. 50.

    50 2. Add 3 images Add copies of 3 unknown

    images U1, U2, U3 to Thingy in realtime www.xyggy.com © 2019
51. 51.

    51 3. Query with 3 unknown images again Unknown images

    U1, U2, U3 Copies of U1, U2, U3 appear in results www.xyggy.com © 2019
52. 52.

    52 www.xyggy.com © 2019 Control with UIX less … and

    many other UIX functions built with API
53. 53.

    53 Roadmap www.xyggy.com © 2019 recommendation engine for all kinds

    of things
54. 54.

    54 We want to: Give people control of their AI

    Enable a new generation of dynamic recommendation services for consumers and enterprises Make dynamic AI a focus of ML research www.xyggy.com © 2019
55. 55.

    55 www.xyggy.com © 2019 “If you use an old tool

    to tackle a problem you’ve got to be really smarter than the rest of the folks because everybody has this tool. If you are the first to look with something new it’s like starting a new world. You just look around and everything you see is going to be new.” Steven Chu, Nobel Laureate, Physics
56. 56.

    56 Dinesh Vadhia dinesh@xyggy.com www.xyggy.com @DineshVadhia www.xyggy.com © 2019