Andrew Yip - Future of Food with AI Technologies

Show video

welcome welcome to another episode of the impact  of ai supported by wilda women leaders in data   and artificial intelligence every week we explore  how ai impacts us personally and professionally   and this week is no different today we're here  with andrew yip he's a food technologist and   also a chef and we're going to explore how ai  could potentially impact food and we're not   going to specifically focus on the food industry  or the supply chain or the point of sale we're   not going to talk about how ai is being used for  drones to harvest you know the food in the farms   but we're going to bring this forward to the  behind the scenes the technology of food and how   ai and ai technologies could be expanding this  space differently and how it's going to impact us   andrew welcome thank you we'd like to start with  your professional journey as both a chef in the   earlier career and how you've transformed that to  your current role which is the future of food okay   all right so i started as a coach  during that time a junior role in a   in a restaurant and progressively i woke  up to the ladder in the kitchen hierarchy   some point of time i know that that's really  more about what i could do within about food so i   diverted my career into a different path where i  got myself a apprenticeship in one of the largest   food company then from there i actually  learned about that's really more than just   about chicken beef soup and etc it's really about  how to create a good product using the available   ingredient and raw material that we  are able to utilize them from the   basic of food building up to  a complete delicious product   so from there actually i see a lot of  interaction between human being and   another human being try to find out the  answer but as we progress on i do realize that   there are possibility of using machine to do it  but it's just not possible during 20 30 years time   but somehow throughout the years especially the  last three years i noticed that there are changes   to this how machine can help us to work so i am  i personally not able to use that facility or the   machine yet but i see there is a great  potential where we are going to hate on from now so as you've progressed from a chef to  then working kind of behind the scenes   your your role really moved into food technology  which is an entire space in itself what is what   is food technology okay food technologies  uh using uh basic raw material of salt sugar   uh certain amino acids and uh using of certain  modified starches spices to create a basic taste   environment for the food product then you build  on to the food structure in terms of what kind   of a food that will be going into for example if  it's a liquid soup then you have more ingredient   using vegetable protein as well as the  starches into that manner okay that is if   the product goes into the soup but then using the  same principle this can apply to uh processed meat   uh it can apply to noodles pastas ready meals etc  etc so a food technologist is breaking down the   components of food and looking at  maybe new ways to experience it another way to put it food technologies uh  enable the manufacturer to have a consistent   uh method of preparation of uh food at the same  time uh safeguard the integrity of the food itself   so that it can be still as delicious and as  tasty as should be but at the same time because   we are talking about mass production so there's  always uh course involved how to bring it down uh   producing more cheaper and faster as usual the  uh the business point of view of producing it   are we going into processed food no  i i believe that always uh how we see   uh processed food as a lesser of evil in in that  manner your current role is the current role you   have is head of future food what is what does that  mean i mean that's that's kind of a really i mean   that could be a very broad broad role it is it is  okay uh this one takes a bit more uh explanation a lot of time we are looking at this  advancement in technology to produce   household kitchen appliances we  see the most recent one about   about seven years ago we have this uh superheated  airfryer instead of a deep frying a very uh   same concept of heating but at a faster speed  and the food can be brown at a faster way   instead of using microwave which you can  heat up the food but you can't really brown   the food itself so air frying is a great  technology to come by but at the same time   we see the induction uh uh stove and things  like that it give the end user the consumer the   homemakers uh uh save a lot of time as well as  in the industry itself we do not need uh the gas   but the electric uh will just able to speed  up the things so what i'm trying to say is   that that's a that's a great improvement  in terms of cooking appliances however   what we are not seeing is how can the food  be improved so that we can have it better   more nutritional more sustainable at the  same time good for the planet and good for us   so in this aspect is about future food what  we're going to consume in future but we're going   to start with now how we're going to consume the  food now that will impact us in regards to every   day can we eat better but more sustainable can we  eat better yet still maintain that deliciousness   so future food is really about how we see food  now how can we change it are we looking at the   perfect apple or can we have it still apple but  we can have it differently but still deliciously   and enjoy the apple that actually brings me to  a something that we wanted to talk about today   is the utilization of ai technologies and  when i say ai technologies i'm talking about   um natural machine learning deep learning  language processing being able to augment   the the human condition faster more  accurately and with you know oftentimes   higher confidence and you mentioned breaking  the food down so that it can be healthier   one of the concepts that we've talked  about earlier was utilizing ai to   create new recipes either improve recipes create  recipes or change the recipes so that the foods   that we're eating today is healthier i'd  like to understand your perspectives of   would ai in this scenario actually provide  more benefits to us okay so uh from the uh   food technology's point of view all the uh food  starts with a basic formulation of understanding   the raw material use now all these oral material  used can be measured and can be quantified   in terms of the quality as well as the  quantity they can be transformed into numbers so if that can be done i see no reason  why it cannot be fit into the algorithm   of an ai and transform them into a  data to be processed by the machine   that is my very simple thoughts of that to  begin with yeah because you mentioned um   because really the food technology  space is i think where we're seeing   more innovation and you mentioned earlier just the  innovation and compliance and how the consumers   you know how the consumer takes the food but  also i think how you know from the behind the   scenes the research and the development i could  absolutely see where an ai technology could take   a food that we currently use today whatever it is  mashed potatoes something that's consumed quite   broadly on a global scale and very quickly run  scenarios and simulations to say hey if we just   make these little bit of tweaks we could actually  serve the same type of mashed potatoes but with   these extra ingredients or with this extra twist  it could be healthier so now individuals consuming   that product hey i love mashed potatoes but it  doesn't really do anything for me now can say i   love mashed potatoes and now i'm getting majority  of my health yes i could provide another example   uh in fact this is what i currently doing so uh in  the space of meat alternative that i'm doing now   we are utilizing soy the soy protein that we  are sourcing uh all over the world but there   are so many that we could source there are so many  data that we could gather there are so many grades   of soy protein in regards to different grades  different protein content and most importantly   where they are coming from within certain  radius of of in terms of the the source   of where this coming from now in order to to have  a very sustainable way to to produce we shouldn't   import and invest too much on the carbon footprint  but in order for us to to narrow down the search   and choosing the right balance between the  price the supply as well as the functionality   of the soy protein if we take human to do  it i'm sure we could do it but it takes a   long long time but if we could feed all this  information and turn it into a data that can be   processed the combination and also the permutation  that comes about will be much faster and the   analysis that done by the machine helps the human  to put things together i see that is a possibility   i want to i want to stay a little bit on the topic  of the alternative meat products or alternative   alternative meat products so these are you know  for everyone listening these are your plant-based   meat industry uh companies like amy's kitchen  beyond meat uh boca foods and i think probably   here in the state something a little bit more  known or more popular is the impossible foods   for example they now have the impossible burger at  burger king and here in the states with starbucks   have the impossible breakfast sandwich now what  i've i've noticed with some of these companies is   you know the the perception of the the alternative  meats and the hasn't really been you know exciting   you know a lot of times the the vegetarians that i  speak with or the foods that i try myself they're   very dry nobody really likes it and then suddenly  technology has burst in the past couple years   where the flavor profiles have been raised  within these alternative meats where   it almost tastes exactly like and it looks  like and it it burns and cooks like real meat   so with your experience in alternative meats have  have you been able to would you have any thoughts   about where that technology is is coming from  or how we've been able to expand that that that   industry sure so let's take a piece of burger to  do as our uh discussion point yes now a piece of   burger we talk about the structure of the burger  we also talk about the uh the colored appearance   of the burger then after that we also need to  talk about how can the burger smell and especially   before cooking during cooking and after cooking  the aroma generated by the burger itself   so all these three aspects and not to forget the  nutritional aspect of the burger itself so it's   really about uh three-dimensional but then again  within that three-dimensional that there's always   a space how can we make the more affordable more  sustainable at the same time make the burger more as delicious as it is if it's not coming from the  animal okay so let's uh let me jump into the the   quickest one in terms of the color the color  can be uh natural colors that we can get from   derived from vegetable process so that one is not  difficult to achieve but to achieve the correct   tone of the color we need a combination of two  or three different colors to make it a much more   vibrant in terms of slightly more closer to  red meat or closer to white meat or dark meat   so the tone of color can be an interesting  combination to begin with in fact it's not   as easy as mixing color a and color b it's  about the different shades of color and   there are some colors can be encapsulated and  come in much later when it's heat activated   and change the color when the cooking process  begins so this uh something that the technology   can help on the food integrity itself class  one yes i i i'm seeing this now oh go ahead yep   yeah so next we move on to the texture now  this is a big topic the texture to put in ingredients to look like a meat is  not as simple as what we used to have   however with the the technology that able  to to come up with certain uh binders and so   that emulsifier and certain stabilizers to  combine the water the protein and the fats   which normally all this street doesn't  add together but the emulsifying effect   through the uh the advancement of technology  the water the oil the the fats as well as the   protein able to come in together very nicely and  firmly and that's where you get the good texture   as close as what animal protein offers now  that's on the texture in a very simplicity way   the third one is about the aroma now which  is the most difficult of all because now   animal protein do inheritantly they  do have certain smell and aroma   and the smell changes as we coat the piece of  burger or chicken however if it is a plant-based   can we do that again the technology will enable  the flavor to activate at certain temperature   point to release certain aroma and as we continue  to cook and it will continue to activate based on   the the temperature itself or  that what we call a time release activation of encapsulation so the longer  we cope to until a certain point of time the   piece of burger will release the full flavor  when it's being consumed by the consumer   so here it goes technology again play an  important role in putting up the flavor together   because you do not want a piece of burger to smell  the same before during cooking and after you would   like it to change like a real animal protein how  can we do that it doesn't happen easily but it   can be done so i think this is a probably a really  good use case for ai technology you've mentioned   you've mentioned breaking food down almost  to its chemical component and specifically   with alternative meats where we're looking at  plant-based well anything you know that's non   let me uh let me rephrase that specifically  looking at alternative products so whether it's   spirulina or some protein that's attaching itself  to a plant under the water all of these things   are not known to us we haven't  experienced cooking with them before   so if i'm looking at this on the other side the  research side i'm taking all of these products   from from around the world that we've never  experienced i'm having to break it down into   its components almost down to its chemical  compounds and then i need to be able to run   simulations after simulations after simulations  with just that product but then i need to also   understand how it's going to combine with other  products and you've mentioned just three and   i'm sure there's more three areas that the the  flavor itself the texture and how it sits and   and contains itself and then also the smell and  how it cooks over time yes i i absolutely think   this is probably the best use case i could i could  think of of where ai could come in and augment   the amount of time that it would take to research  all of this into a shorter period of time   right so when i i'm leading a team currently  i'm leading a team of food technologies so   one of the reminder i always tell them do not  have too many variables keep your constant and have a not more than two variable as you do  on the trials now there's a lot of permutation   but with the experienced food technologies they  will know how many trials they could they will   do to achieve certain results but again if we talk  about a new product if we talk about a ingredient   that we never used before you talk about uh  evaluation of certain uh replacement product   that's a lot of trial and error and after  that we will have to really taste them   in order to give a correct organoleptic sensory  evaluation so this takes a lot of time okay so   whereby if we have certain uh all these  are being captured in in numbers when   we taste certain product we are giving them  scores we are giving them a very meaningful   evaluation based on sensory data and that is a  huge topic itself sensory data science that can be   also be used by the machine interpret and analyze  by the machine the algorithm will have a good uh   how to say to give the the meaningful  interpretation of what the numbers are   so in this case it will help us from the food  technologies point of view to come up with   certain permutation faster without going through  all the series of work that i mentioned earlier you mentioned earlier the the sense of of smell  and i and i know that taste and smell often play   a very have a very close relationship with  each other i i was reading online and i i'm   gonna paraphrase because i don't uh have the exact  quote but online there was a chef that mentioned   that the sense of taste is best in the morning  when it's been unencumbered by other things and   as we go throughout the day that sense of taste  waivers and it becomes less and every time we   eat something else that sense of taste gets  less and less throughout the end of the day another use case that i i think  that we've we could probably   discuss is how we could use ai to  understand the flavors of the food   and then be able to impact how  we consume it throughout the day yes that is true as what you said you currently  pointed out it's best to taste uh our senses are   more sensitive more acute uh in the morning so  there's a sensory fatigue as with days goes by   because it's the same tongue that we have and we  can't change another time so we just have to use   back the same one and that relies on the the the  memory that we have to taste so there's always a   sensory fatigue cake skin so best that is taste  in the morning as we speak now they are already   companies especially dealing with  flavors and chemicals already using aai   to process the data to come up with a  better flavor a better combination of   chemical molecules combination  of them to come up with a more more price sensitive flavor  more stable flavor that can uh   withstand certain uh heat resistant and also  the flavor can be the smell and the flavor can   be more closer to what the orig the natural  food product brings for example strawberry   strawberry is not difficult uh to to  identify as a strawberry right strawberry   jammy or strawberry sweet and all strawberry it's  just plain raw but how to get all this right in   in the shortest time ai can do that i strongly  believe that i know they're already happening you know i i i just thought about this who  determines what food tastes good and i never   i never thought about that until just now  but but i was at a restaurant the other day   and you know my one daughter loved the the food  that i was eating and another daughter tried it   and she's like yeah i don't like it and if we're  talking about and if we're talking about a.i   and how ai could impact the  flavors or the the sense of smell we still need to have a human behind the scenes  that that says yes that's that's the flavor   we were going for i mean it sounds like the  the ai technology is there to maybe augment   the simulations and run those permutations and  variables but it's not replacing the chef it's   not going to replace the food technologies  because somebody needs to physically   be there to say yes this strawberry tastes exactly  the way it should even after we've done all of   these things to modify the strawberry yeah the  hell does that of the machine take away my job   no uh something that we do it almost every  day so when we taste a food product uh   still in the early development stage we  make sure that uh all the comments or the   uh ranking of how strong is  the the strawberry notes okay   how we describe the strawberry notes and  how this strawberry uh uh is it a sweet sour   and all all these valuable comments are being  captured so we do spend time uh process them   now ai will help in this manner but ai will  not tell you until we feed the ai sufficiently   to form uh the big data that they have what is  called uh sour that is always a threshold that is   good for human being certain sourness a strawberry  if it's not certain do not have certain acidity   do not carry certain sourness it is not a nice  strawberry but a strawberry that has upfront   sweetness but in the sweetness it carries an  undertone of sourness and also a sweetness   lingering behind after taste that is a good  strawberry now how can we achieve that until we   feed the ai with certain threshold  that we determine the threshold   then the ai will in return process that  and help us for a faster processing yeah i lost you no no i'm i'm i'm   i'm thinking i mean i've got food now in my  head so i've got all these things going on the other the other piece that i was  thinking of is the the combination of foods   for example when i eat a peppermint leaf yes i  i get that peppermint flavor but when i eat a   peppermint leaf and i eat it with some very dark  chocolate i've noticed that the peppermint is more   peppermint the the flavor of the peppermint  is raised you know to the a different level   so i i'm thinking another use case here  is is certainly the combination of foods   and how we combine foods together or how a  restaurant would put certain foods on the plate   to be more to be more adaptable but maybe to  combine together and create something better okay   yes in fact uh it's already happening  okay it's what we call uh food pairing   okay what best who who does who decided that  chocolate pairs well with peppermint yes   right yeah okay so this one is ho uh combination  somehow but what we are talking about could we   have new pairing for instance so uh  this one actually uh championed by   hayson blue mentor a very renowned chef in uk he  pairs caviar with white chocolate okay it goes   very well trust me i tasted that okay but i'm  sure i'm sure there are a lot more combination   that we do not know of but as we speak uh what i  know there's some groups of scientists as well as   food technologists and also chefs who are talking  about cultural differences behind each food   pairing why does it pair why they are bringing in  much more than just why this food pair with this   they are bringing in the cultural the geographical  the the place where they grow certain food so they   are putting all this information and surprisingly  uh the according i i did read an article   in terms of food pairing they are  differences between the west and the east the west would like to just look for a  good pairing in terms of two kinds of   food that means food a and food b share  certain similarity in terms of molecule   that's a good combination of food pairing but they  discovered in over the eastern side a lot of food   do not need the similarity of molecule to pair  the food so in this combination the food a and   the food b have totally no relationship between  whatsoever in terms of molecular level however   they are using a third food that means the  food number c as a bridging flavor so they   able to classify in terms of geographical area  the north asia and the south asia and over the   european side and usa which country or which  continent will have this tendency to pair   flavors based on the same molecular structure and  which country or continents would like to pair   food based on the third party that means the food  number c as a bridging flavor to bring the the   combination of food together i am blown away with  this kind of result but in order to achieve that   no way and no amount of human analytical mind and  also the time to process all these data you've   got to be ai behind this yes i'd i didn't even i  mean i'm i'm not a food technologist i just really   like food and i didn't even think about  some of the the nuances and the the the   additional variables that you just brought up  that just looking at food at a molecular level   and how it impacts culturally and you're not even  really talking about you know one point yeah the   us versus you know asia pacific but you were also  talking about the nuances within that asia-pacific   geographical area that's that's pretty  amazing that that's a lot you're right   it's a lot of data then in fact i i just wish  okay they are probably they're already being done   how can the nutritional value  could impact the food combination   at a very affordable way because nutritional  foods at times not that affordable that's one then   how could when we combine food especially from  a food preparator point of view when we combine   food how can we make sure that whenever the  ingredient we use are sustainable and actually uh   much reduced carbon footprint can we do that  before we actually start cooking can we do a   simple planning when we do the shopping on on the  grocery for for for the food can we do that uh   only i can only choose from certain uh area or  certain list that are all sustainable within   300 kilometers radius not more than that could we  do that could we narrow down 250 kilometers radius   so this this all this information uh uh are  useful it's not that a chef doesn't care about   global warming or environmental awareness but we  need the tools to enable them to do so well i'm   glad you're thinking about this um because you've  taken it one step further it's not just looking at   how ai can impact the food the taste i mean we've  talked about taste we've talked about texture   we've talked about how the food changes when it's  cooked or and you've even referenced that how it's   cooked differently whether it's in a fryer air  fryer whether it's an induction versus gas versus   electric but but now you're taking that one step  further and how ai could impact a more nutritional   value at a price that's affordable for everyone  and i i think that's just an amazing concept   yeah so this is all about how can we do it better  that's why i'm in this space of how can we search   for a better way to do things better way  to to cope better way to manufacture food   that's what future food all about i think that  what i've learned today is that ai is not a trend   in in this space in food technology it's  something that's really going to help   the food technology space evolve probably  more quickly in the next couple years   but i'm seeing it move away from a trend so  trend for me is there are pockets where maybe   this is being used and i i could see it evolving  into something more of a permanent reality but   what i've also learned today is that you are not  going away that just because ai has a a variable   calculation that says this is what it's supposed  to be we still need the the human interaction we   still need you as that food technologist to ensure  that that's the right combination to ensure that   it is sustainable to ensure that it is going to  provide that nutritional value and it's affordable   yes i strongly believe that technology is a  double-edged sword it's just how we're going to   use it and i believe that with ai is really about  it should be helped us better to to deal with   food especially to be honest our food  system is a broken pieces it needs to fix   i i'm i'm i just hoped uh there are  people are working on it i'm working on it   in in a very small way but we just need to  fix our current food system it's not that   we got not enough food it's about how we're  going to distribute the food it is totally   different topic i understand but it's really  about the entire food system that how can we   make it better for for everyone on this  planet so as we we wrap up where do you   what do you think is next i mean you're  in you're in this space what's next for   for the future of food where is this going  at this moment we are looking at how can we do something a very small way of  doing it meaning by changing the way   people eat that is something we i'm doing now  and what's next as to answer your question   it's really about making it much more affordable  but still maintain the integrity of the food after   all we are not human not talking about if i will  save the planet i'll pay through my pocket without   tasting it good the taste is still the paramount  of every food technologist to make it tasty to   make it delicious and get to to safeguard the  integrity of the food itself so the future is not   not to happen totally entirely new food but  how to have a similar taste better quality   better nutritional and much more affordable  that's wonderful do you have any final thoughts my thought yes i do hope that  how can we distribute the food   much better food wastage is the my main  concern is how can we fix that food waste yes you mentioned earlier about  changing the way we eat   does that somehow connect with your comment  about wanting to reduce the the food waste   yes because when we choose certain ingredients to  go into preparation of food it begins from there   are we able to make a better decision so that we  do not waste food during the processing that's one   can we select certain raw material and can have  a better shelf life so that we do not waste food can we make sure that when the expiry  date is being uh stated as of today uh   this is going to expire how how can we change that  is it because the the law said so or because they   have gone through a series of tests that's that's  a lot of uh because we have to abide by certain   food regulation and that's where the food weighs  i witnessed that we throw away food because it's   just stated that it hit the expiry date without  even assessing whether it is still good or not so this is something is yes we are abiding  by the food law that's fortune no doubt   but how can we do better how can we prevent  this from from the very beginning but   if we come to that stage how can we  process that kind of thoughts by not   just deciding to throw away the food all these  uh uh i have honestly i have no answers for it   but it's really can we not look at  it in in a different perspective   and upcycle it into a different differently so  it's really about how to re reduce is the the   way stage to begin with but before we reduce  the wastage how can we do a better selection   from a start and that's something right that's  something yeah no i i i hear the passion i i think   this is in it i i understand it's there's i i  think what we've learned today is there's so much   still to be undiscovered around food and so many  areas within the the food life cycle that can be   improved in pond and not just what we're talking  about at the earlier part of the conversation   the impact to the consumer which increases  profits or helps reduce the affordability   for that consumer the taste the texture the  alternative proteins trying to feed more people   around the world but i think you've also hinted  that there's a responsibility you know part to   this there's the distribution to individuals  that maybe perhaps can't reach the food that   we're we're producing and more importantly the the  waste of the food that you've mentioned and here   is i think another another really  good use case for ai yes yeah okay   i really appreciate your time today i know that  you and i are completely in the opposite time   zones of the world at the moment uh thank you  so much for staying up late to be a part of this   and i would love to have another opportunity  to talk with you in about a year from now on   the same subject because i have a  feeling based on what you're doing   things are going to be moving quite quickly  within the food technology space okay i'll i'd   love to yeah i'd love to yeah great thank you so  much for your time today thank you marisa thank

2022-08-04

Show video