View source for DT's page for Kahn Food project

--[[User:Thiebaut|D. Thiebaut]] ([[User talk:Thiebaut|talk]]) 09:20, 7 December 2017 (EST)
----
<onlydft>
=News=
* François Chollet, Google, @fchollet
:::There's a point to be made that a neural network for food classification that can classify Tide pods as "not food" has already reached superhuman capabilities, Twitter, 6:30 PM - 20 Jan 2018
<br />
=Reference=
<br />
* [https://www.smith.edu/kahninstitute/future.php Page for Kahn future projects]
<br />
=Short Presentation for Kahn=
<br />
* NN + ML = branch of AI
* Huge progress at exponential rate
* Example: [https://www.sciencealert.com/it-took-4-hours-google-s-ai-world-s-best-chess-player-deepmind-alphazero In Just 4 Hours, Google's AI Mastered All The Chess Knowledge in History].  AlphaZero. 
<blockquote>
In a series of 100 games against Stockfish, AlphaZero won 25 games while playing as white (with first mover advantage), and picked up three games playing as black. The rest of the contests were draws, with Stockfish recording no wins and AlphaZero no losses.
</blockquote>
* ML applied to many different areas: chess, self-driving cars.   Why not look at how it's been applied to food.
* Areas where ML is being applied to food
::* Classifiation
::::* Beer classification (12 parameters)
::::* Classifying products as drugs or non-drugs
::::* Classification of different types of honey
::::* Classification of cereal grains acording to morphological features
::* Recipes
::::* MIT AI Recommends a recipe based on a photo of food
::::* IBM Watson (winner of Jeopardy) learns all recipes from Bon Appetit and generates new recipes
<br />
Interested in exploring, and cataloguing  the different areas where ML has been applied to food.
<br />
=Good History of AI/NN=
<br />
* [https://www.ibm.com/developerworks/library/cc-beginner-guide-machine-learning-ai-cognitive/index.html  Introduction] Timeline of modern AI Foundational AI Machine learning Cognitive computing, A beginner's guide to artificial intelligence, machine learning, and cognitive computing
<br />
=Food Classification=
<br />
Some results from the Google scholar search on [https://scholar.google.com/scholar?q=food+classification+neural+network&hl=en&as_sdt=0&as_vis=1&oi=scholart&sa=X&ved=0ahUKEwjghZ_TjfjXAhWENiYKHVhyD58QgQMIJTAA "food classification neural network"]
<br />
* Beer classification: [http://www.sciencedirect.com/science/article/pii/S0003267011008622 Application of artificial neural network in food classification].
<blockquote>Artificial neural network (ANN) classifiers have been successfully implemented for various quality inspection and grading tasks of diverse food products. ANN are very good pattern classifiers because of their ability to learn patterns that are not linearly separable and concepts dealing with uncertainty, noise and random events. In this research, the ANN was used to build the classification model based on the relevant features of beer. Samples of the same brand of beer but with varying manufacturing dates, originating from miscellaneous manufacturing lots, have been represented in the multidimensional space by data vectors, which was an assembly of 12 features (% of alcohol, pH, % of CO2 etc.). The classification has been performed for two subsets, the first that included samples of good quality beer and the other containing samples of unsatisfactory quality. ANN techniques allowed the discrimination between qualities of beer samples with up to 100% of correct classifications.
</blockquote>
* NN used for drug/nondrug classification
* NN used for the classification of honey
* Classification of milk
* Evaluation of neural network architectures for cereal grain classification using morphological features
<br />
=Recipes=
<br />
* [http://news.mit.edu/2017/artificial-intelligence-suggests-recipes-based-on-food-photos-0720 AI suggests recipes based on food photos].<br />  
<blockquote>
Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) believe that analyzing photos like these could help us learn recipes and better understand people's eating habits. In a new paper with the Qatar Computing Research Institute (QCRI), the team trained an artificial intelligence system called Pic2Recipe to look at a photo of food and be able to predict the ingredients and suggest similar recipes.
</blockquote>
* [https://spectrum.ieee.org/tech-talk/robotics/artificial-intelligence/ibm-watson-learns-to-cook-from-bon-appetit-magazine IBM's Watson Learns to Cook from Bon Appetit Magazine]
<blockquote>
In a just-announced collaboration with Bon Appetit, Watson is using the 9000 or so recipes in the magazine's database to generate new recipes based on available ingredients and a suggested cuisine style. The AI uses both the magazine's archive and its own database of flavor compounds to determine what ingredients will go well together, and comes up with surprising new combinations. For more on how this works, check out the [https://spectrum.ieee.org/computing/software/creating-recipes-with-artificial-intelligence IEEE Spectrum article] about IBM's cooking initiative for Watson from last year's special issue on food and technology. 
</blockquote>
* [https://spectrum.ieee.org/computing/software/creating-recipes-with-artificial-intelligence Creating Recipes with Artificial Intelligence], IEEE Spectrum, May 2013.
* [https://www.dailydot.com/unclick/neural-network-recipe-generator/ A scientist is trying to teach a neural network to cook—and the results are hilariously bad]
* [https://www.theverge.com/tldr/2017/7/20/16005826/mit-csail-recipes-ai-neural-network-algorithm This MIT neural network translates pictures of food into recipes]
* [https://boingboing.net/2017/04/05/517414.html Neural network comes up with crazy food recipes]
* [https://www.theguardian.com/technology/2016/jun/04/man-v-machine-robots-artificial-intelligence-cook-write Man v machine: can computers cook, write and paint better than us?]
<br />
<center>
<videoflash>V1eYniJ0Rnk</videoflash>
</center>
<br />
=Videos=
<br />
{|
|
<videoflash>V1eYniJ0Rnk</videoflash>
|
Found in [https://www.theguardian.com/technology/2016/jun/04/man-v-machine-robots-artificial-intelligence-cook-write Man v machine: can computers cook, write and paint better than us?]
|-
|
<videoflash>aA0SUN7LMuQ</videoflash>
|
Youtube video: Indian Food Image Segmentation and Classification using Color+Texture Features and Neural Network.
|-
<videoflash>IoC4rwnZxH4</videoflash>
|
MIT's AI System "Pic2Recipe" Predicts recipes from photos | QPT
|-
|
[[Image:NN_birds_blaise_aquera_y_arcas.png | 450px]]<br />
[https://www.ted.com/talks/blaise_aguera_y_arcas_how_computers_are_learning_to_be_creative/up-next#t-705406 TED talk by Blaise Aquera y Arcas]
|
How computers are learning to be creative.  Very good intro to how NN work, at 6 minutes 27 sec.
|}
<br />
=Schedule=
<br />
* Options
** Thursday 5:30 - 8:30 p.m.?
** Friday lunch +
<br />
=Ideas=
<br />
* MIT food researcher
* Michael Pollan
* Anthony Bourdain, Parts unknown 
* Amherst survival center?
<br />
* April 30th, May 1st, major 2-day activities for 2 current Kahn projects 
<br />
<br />
<br />
<br />
<br />







</onlydft>
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
[[Category:Food]][[Category:Kahn Institute]]