Slide 1

Slide 1 text

Appearances Matter: AI Learning from Text and Images Gerard de Melo http://gerard.demelo.org Appearances Matter: AI Learning from Text and Images Gerard de Melo http://gerard.demelo.org https://commons.wikimedia.org/wiki/File:Muliple_colored_pencils_07.jpg

Slide 2

Slide 2 text

https://zh.wikipedia.org/zh-hk/ 柏林

Slide 3

Slide 3 text

Image: Diana Parkhouse

Slide 4

Slide 4 text

Image: Diana Parkhouse

Slide 5

Slide 5 text

Learning from Examples Learning from Examples Learning from Examples Learning from Examples cat

Slide 6

Slide 6 text

Learning from Examples Learning from Examples Learning from Examples Learning from Examples KI lernt anhand von Beispielen AI learns from examples.

Slide 7

Slide 7 text

Learning from Raw Data Learning from Raw Data Learning from Raw Data Learning from Raw Data Image: Olga Andreyanova

Slide 8

Slide 8 text

Learning from Raw Data Learning from Raw Data Learning from Raw Data Learning from Raw Data An Example Pair to Learn from Image: Olga Andreyanova

Slide 9

Slide 9 text

Learning from Raw Data Learning from Raw Data Learning from Raw Data Learning from Raw Data Berlin ist eine lebendige Stadt.

Slide 10

Slide 10 text

Learning from Raw Data Learning from Raw Data Learning from Raw Data Learning from Raw Data Berlin ist eine lebendige Stadt. An Example to Learn from

Slide 11

Slide 11 text

Image: https://500px.com/photo/96738645/street-bookstore-by-pablo-tarrero Learning from many millions of examples

Slide 12

Slide 12 text

Mouse brain microscopy, adapted from Na Ji, UC Berkeley Neural Connections in the Brain

Slide 13

Slide 13 text

Learning Models Learning Models Learning Models Learning Models

Slide 14

Slide 14 text

Connecting Vision and Language Connecting Vision and Language Connecting Vision and Language Connecting Vision and Language x x x x A cat sitting on a mat looking out the door https://commons.wikimedia.org/wiki/File:Nebelung_cat_looking_out_door.jpg / https://commons.wikimedia.org/wiki/File:Dog_costume_parade_in_Sunset_Park_%2816432%29.jpg A dog wearing a USPS mail carrier costume

Slide 15

Slide 15 text

Generation Models Generation Models Generation Models Generation Models

Slide 16

Slide 16 text

Generation Example Generation Example Generation Example Generation Example

Slide 17

Slide 17 text

Generation by Generation by Combining Vision and Language Combining Vision and Language Generation by Generation by Combining Vision and Language Combining Vision and Language Teddy bears working on new AI research underwater with 1990s technology https://commons.wikimedia.org/wiki/File:DALL-E_2_artificial_intelligence_digital_image_generated_photo.jpg

Slide 18

Slide 18 text

Challenge: Challenge: Responsible AI Responsible AI Challenge: Challenge: Responsible AI Responsible AI Responsible Use of AI Image:Kev Costello

Slide 19

Slide 19 text

Human Understanding Human Understanding Human Understanding Human Understanding DeeepMind’s TAP-Vid

Slide 20

Slide 20 text

Learning from Videos Learning from Videos Learning from Videos Learning from Videos Geng et al. Character Matters: Video Story Understanding with Character-Aware Relations

Slide 21

Slide 21 text

Masked-Piper. Babajide Owoyele, James Trujillo, Gerard de Melo, Wim Pouw (2022)

Slide 22

Slide 22 text

Understanding Human Perception Understanding Human Perception Understanding Human Perception Understanding Human Perception Tugba Kulahcioglu, Gerard de Melo. Predicting Semantic Signatures of Fonts

Slide 23

Slide 23 text

Understanding Human Perception Understanding Human Perception Understanding Human Perception Understanding Human Perception Van Rompay and Pruyn (2011) + de Sousa et al. (2020). Journal of Sensory Studies Choice of font affects brand credibility, price expectations, even assumed acidity, sweetness

Slide 24

Slide 24 text

Understanding Human Perception Understanding Human Perception Understanding Human Perception Understanding Human Perception Tugba Kulahcioglu, Gerard de Melo. FontLex: A Typographical Lexicon based on Affective Associations / Tugba Kulahcioglu, Gerard de Melo. Paralinguistic Recommendations for Affective Word Clouds. Proc. IUI The Smurfs Scream

Slide 25

Slide 25 text

Understanding Human Perception Understanding Human Perception Understanding Human Perception Understanding Human Perception Contentment Fear Dobler et al. Art Creation with Multi-Conditional StyleGANs

Slide 26

Slide 26 text

Towards Trustworthy AI: Towards Trustworthy AI: Medical Applications Medical Applications Towards Trustworthy AI: Towards Trustworthy AI: Medical Applications Medical Applications

Slide 27

Slide 27 text

Towards Trustworthy AI: Towards Trustworthy AI: Daily Life Applications Daily Life Applications Towards Trustworthy AI: Towards Trustworthy AI: Daily Life Applications Daily Life Applications Where’s the nearest exit?

Slide 28

Slide 28 text

Image: Adapted from https://techcrunch.com/2017/12/22/fin-assistant/ Contact: http://gerard.demelo.org linkedin.com/in/gdemelo