To access all our features please use the Goodpods app.
Open the app
Design for AI
Top 10 Design for AI Episodes
Best episodes ranked by Goodpods Users most listened
8-Will AI make UX design obsolete?
Design for AI
10/23/19 • 0 min
We cover changes that are coming to the UX field because of AI. We look at how design, research, and UX management will all need to adapt to new processes.
TranscriptsI’ve gotten this question. So the scenario that everyone seems to come up with is: Sure at first it was just the repetitive jobs that got replaced by AI. Then GANs started generating everything. Who needs a designer when a computer can put out 1000 designs a second? Right? Obviously, I wouldn’t be talking about this if I thought this was a problem. Today we are covering how AI will change UX and design This podcast is called design for AI It is here to help define the space where Machine learning intersects with UX. Where we talk to experts and discuss topics around designing a better AI. music is by Rolemusic Im your host Mark Bailey Lets get started music I want to start with an example Everyone knows of deep blue, the chess application that first got everyone’s attention by beating the best chess player. Since then AI has beat the best Go player and can beat anyone at competitive video games. But do you know who has beat the AI systems? Human and AI hybrids. The top ranked chess systems right now that can beat any AI out there are all human-AI hybrids. The human brain and an AI system both make shortcuts. They do them in different ways. They do better filling in for each others weak spots. The best system is always augmented, not replacement. I’m not the only one who thinks this IBM CEO Ginni Rometty recently expressed that “If I considered the initials AI, I would have preferred augmented intelligence.” Now while AI isn’t going to take over UX, or make it obsolete, I do think a lot will change. In the scenario I talked about GANs generating 1000 designs a second. This is actually the case, they can. But automated generation doesn’t mean good. A few years back there was a company that promised to get rid of the need for website design, called The Grid. It delivered underwhelming results. But, you might ask it could get better from another company. Google tried something similar. You may have heard of them testing 42 shades of blue against each other to get just the right blue with the best response rate. That was successful. But when they tried expanding the analytics based design past those very basic items they kept hitting a wall. So why is this the case? To get better AI we need better UX There is mutual benefit on both sides that run in a cycle.
- As AI starts getting used more,
- The ML model produces more data that is useful
- The new model is trained off of that data
- AI becomes more useful
- ML models start spouting up delivering unneeded advice and tasks which just add to confusion instead of solving problems
- The need for a better UX becomes more important
- A better UX is created and refined
- AI gets used more, the cycle starts again.
DesignFor the designs you do create, nothing new here, but concentrate on empathy. The problem with ML models is understanding humanness. How can you figure out for the app to react to users current context and mood? Some of the cutting edge research right now is called ensemble models. The basic idea is that ML models are good at doing one thing well, so if you take a bunch of models and put them together and add another model to make a decision for which model to use it creates a more robust experience. This is what needs to be designed. Every change in context is going to need a different ML model. As part of knowing the context, I covered previously to know when to tell jokes. That depends completely on context. ...
We show how the normal software development cycle does not work with AI and how the modified dev model needs attention from UX at every step
TranscriptsHere is the scenario for this episode: The boss gives you access to the companies data and asks you to come up with a model that uses it. With all this data it’s got to be good for making something the users will use right? You buckle down, work with data scientists and make a lot of tweaks to the data come up with something, but no matter how much you advertise it no one wants to use it. Back to the drawing board. This time you find out what the users do want, more tweaks to the data and get a model that is accurate. People love it, tons of users flood in and flood the server. The servers crash from too large of a model. The IT guys say they can fix it and bring in a bunch of new hardware. It all seems to be going fine until you notice every review of your app laughs at how inaccurate it is. This can’t be, it’s the same model, just running on different hardware, right? Lets make sure this doesn’t ever happen. Today we are covering the development cycle for AI This podcast is called design for AI It is here to help define the space where Machine learning intersects with UX. Where we talk to experts and discuss topics around designing a better AI. music is by Rolemusic Im your host Mark Bailey Lets get started music Machine learning up to this point has been more on the research side. So much so that it really doesn’t fit in to the normal software development cycle. There are all these gotchas that won’t let you fit into the normal cyclic agile sprints that most people are used to. This affects getting in good design. A big part of UX design not slowing down the software development cycle is to have a regular process so UX can run in parallel to development. It is possible with machine learning development, the cycle just looks a little different. The normal software development process is building a machine. It’s a really complicated machine, but in development terms it is still stateful, so development is done to by writing to the test case. For the updated process, instead of a machine, think of it like you are hiring an employee. There are 5 stages to hiring an employee.
- This is laying the groundwork
- lay out the job listing – what are the requirements?
- Find Objectives, why are you hiring them?
- Job posting
- What is the purpose & design
- Set your goals
- Define benchmarks
- Build On Expertise
- Collect representative data
- Build the model
- Data scientists train the model
- Train – The model is watching how you do things
- Reinforce Education
- Subject matter experts train the model
- Shadow – You are standing over their shoulder.
- Build Trust
- AI leads task
- Subject matter expert manages AI
- Set your goal
- Define benchmarks
Design for AI
10/09/19 • 21 min
Why creating a personality for your AI is important, be it recommendation system or AGI. We cover the steps needed to evaluate your system and come up with the best personality for your users..
Background research linkshttps://blog.prototypr.io/a-guide-to-developing-bot-personalities-c6eba213d77b?gi=88dd055fd56b https://chatbotsmagazine.com/designing-a-chatbots-personality-52dcf1f4df7d https://medium.com/the-charming-device/how-to-design-intelligence-3-ways-to-make-human-centered-bots-76c5ff7524df
TranscriptsToday’s episode is about personality, So I thought it best to start with a scenario: For example, you are in the market for finding a lawyer, and like most people looking for a lawyer you need to watch your money. you’ve heard good things about some companies providing virtual lawyer services. You download one since it was the top rated since it was so friendly. You get started telling it about the background and back and forth is full of jokes from the lawyer. But the jokes just seem off. Then you need to find some more info and take the device down into the basement the virtual lawyer says it lost its network connection and just starts laughing maniacally. Maybe somebody finds this funny, but if they messed up this bad on the humor, you have no confidence that they got the legal part right. Delete that one, obviously friendly was not the way to go. You download the next one rated totally professional. You start the process but it is taking forever. You have to go through one question at a time. This thing feels like it is reading war and peace off of a DMV form. You find yourself getting lost in the monotony and realize you skipped over the most important nuance. This isn’t professional, this is fingernails slowly scraping a blackboard. Ugh, there is no way you’ll make it through the process and remember everything. Another failure, money wasted, and you still need to talk to a lawyer. Lets make sure this doesn’t happen. Today we are covering personalities for AI This is design for AI a podcast to help define the space where Machine learning intersects with UX. Where we talk to experts and discuss topics around designing a better AI. music is The Pirate And The Dancer by Rolemusic Im your host Mark Bailey Lets get started Today we are discussing how to design your AI personality. We will cover the process step by step for what is important and what to avoid. Some people associate finding the right personality with something hippy or new age. This is not that. If you want the book answer, the personality is the distinctive tone, manner and style in which your app will communicate. It is defined by a set of attributes that shape how it will look, sound and feel. The right language, and tone that embodies your app and differentiates it from the competitors. Look, there is a good chance your app and company already have a personality. Your current web or app design already defines the personality of the company. Color choice, type choices, UI layout, documentation, errors all make up the brand. Basically, it’s the company personality that dictates the brand. So the next step is to use that personality, that up to now has been used for the brand, and to translate that over to training the AI. There are some companies that don’t have a personality right now. The reason being is a lot of companies might not have defined a personality up to this point is because of they’ve used a template for their site or app. There are a lot of templates for websites or using default frameworks for building the widgets for apps. There just isn’t a template for this yet in AI. So going to the trouble of creating a personality has to be done on a case by case basis still. Because the world does not need another Clippy. It was an avatar that tried to keep it light by telling jokes along with the help it gave. The problem was the brand for Microsoft Word is much more corporate which created anger at the unexpected behavior. Jokes or wacky interface quirks can only increase user’s interest or desire to explore in the application if it what they are expecting. Personality sells though, so it will pay for itself if you get it right. People can tell when a company has enthusiasm and passion for what they’re doing. The tide will turn soon enough where t...
5-Michelle Carney, founder of MLUX
Design for AI
10/02/19 • 43 min
I talk with Michelle Carney, founder of MLUX. Lecturer for AI design at d.School at Stanford, and Sr UXR at Google AIUX group. We discuss resources available and needs that have not been filled yet
Machine Learning and UX (MLUX) Meetup Resources:
- Google’s People + AI Guidebook
- MLUX meetup (you can see all of our past talks here!)
- MLUX youtube (all of our past recordings!)
- MLUX twitter (@mluxsf)
- MLUX linkedin company page, community group
- MLUX patreon (All of their events are FREE and they’re trying to get others who might not have access opportunities to speak to our community!)
4-Improving the UX of conversational UIs
Design for AI
09/25/19 • 13 min
We cover all the steps needed for creating a conversational UI like a chatbot or Siri, Alexa, Google voice, and Cortana. We make sure to cover making a plan so a good user experience is the top priority.
Hello and welcome to Design for AI, I’m Mark Bailey, Welcome to episode 4
Let’s talk conversational UI.
A lot of people think chatbot, other people think Siri, Alexa, Google Voice, or Cortana.In the current gold rush climate that is AI right now, it seems that the first step a lot of companies dip their toe in. Sounds like a good topic to cover to me. So I’ll cover the steps that need to be covered to avoid mistakes.
1st step: start with a plan.
If you want to have a conversational interface you need a plan. Think of a good plan as a stop off point on way to voice interaction that everyone says is just around the corner. More likely though is to think of the plan as a list of immediate needs, then turn that around and look at it from the users point of view. Who uses a conversational UI? People using voice interfaces right now, they don’t want to be bothered. They don’t want to be bothered to wait to talk to a live person, bothered by downloading your app, bothered by opening their computer, not even bothered to get off the couch. Your UI needs to make their life more convenient. the way to think of your plan is, how will you get what you need AND make it more convenient for the user?
The first part of the plan is how this benefits your company. What is your motivation for building the interface. Your reason will be specific to you. So I can only cover the general cases. It could be for improving media buy by understand customers, or reducing call center time. There are a lot of Industry specific choices. Conversational UIs are easier to apply to certain industries more than others. Some of the easy industries for this kind of interface. If you are running a CRM, then reduce call center times. For IP established media, the personality is already there. There are set expectations on what to expect so it makes the personality a lot easier.
The next part of coming up with a plain is deciding what to measure. Again this is very specific to your industry. Do you want to know the length of engagement? should it be higher or lower? Do you want to increase return users A lot of the time you will be getting some analytics about the user. Do you want to compare info gathered through your UI to analytics info in user profile? What can you add to the user profile? Do you want to increase the number of recommendations made to other people. No I’m not talking about Net promoter score. I’m talking about use referral codes to get real numbers. You can even measure emotions on users leaving.
Once you have your plan
The next step you need is a DMP – Data management platform, to store the info you are collecting from your app. If you do not have one, now is the time to create it. You probably want to hire a data scientist because DMPs can have a high noise level. Because really, to get any usefulness out of them you will need to be running experiments with the data. DMPs work better better when cross referencing information against each other instead of straight search. Also now is the time to try rolling your own natural language processing project, known as a NLP. Siri, Alexa, Google voice, Cortana all have their own sandboxes that are not compatible with each other. You can try developing for a couple of them to see the differences between the systems. Or a good one open source one to get started with is called Mycroft.
So now that you have a plan and a platform to move forward with, what’s next? You need to create a personality. This is going to depend heavily on your company brand, and what you are trying to accomplish. Think of what is going to be the motivation for the AI you are building. What their motivation is will affect how they answer and guide the conversation. It also depends of the situation your users will be in while having the conversation. You don’t want a mechanic in the middle of a job getting asked 100 questions to get the response they want just so they don’t need to clean off their hands . It might sound like we are designing a person, and there is an argument that goes back and forth on how human you should make your your AI. It is too much to talk about here so I will cover that in a future episode.
short story is don’t fake being a real person. Also know that personality and humanness are different. In this case we want a strong personality, so what’s motivating your AI to give the answers it gives is important. A strong personality is important because it helps to hide the holes in the AI, but not in th...
3-How to use privacy to improve the UX of your AI apps
Design for AI
09/18/19 • 13 min
I talk about how to get privacy to improve the UX through federated learning.
- Google announcement for Federated learning
- Apple announces privacy for their AI models using Differential Privacy
Hello and welcome to Design for AI
Im Mark Bailey, Welcome to episode 3
Today we will be talking about federated learning.
There is a good chance some of you are wondering what it means,
don’t worry it’s still considered a pretty new topic in AI.
Even the word isn’t pinned down, Apple calls it ‘Differential Privacy’.
so I’ll jump right in to explaining what it is and why it’s important to UX.
The old way, or I guess I should say the normal current way,
most models store data used for machine learning
is to round up all the data you think you’re going to need + data attached to it
then all gets uploaded and stored on your servers.
This is the centralized model
There is the saying going around that data is the new oil,
because the more data you can get your hands on
then the better the accuracy is for your model.
Which means you’re at the front of the line for the gold rush,
Well, not so fast
There are problems
Some people refer to data as the new plutonium, instead of the new oil
There is a high liability for personal data
Releasing an app over the internet is global.
But, laws and regulations change by country.
The new EU privacy laws like the GDPR conflict with the laws in authoritarian countries where they want you to share all your data.
In steps the idea of federated learning
As a quick side note, I am using Google’s term federated learning,
instead of Apple’s term Differential Privacy.
Differential Privacy is a little more inclusive of making things outside of machine learning models private,
so in the interest of keeping things as specific as possible I’ll use the term federated learning
to keep things as specific as possible.
I’ve included links for both Apple and Google’s announcements in the show notes.
Anyway, it is easiest to think of it in terms of using a cell phone,
because that is where all of this got its start for both companies
On device storage is small and there is too much data to upload over a slow network
The phone downloads the current AI model.
Then it improves the model by learning from all the local data on your phone.
Your phone then summarizes the changes as a small update.
Only this small update is sent back instead of all the data.
For a non-phone example think of Tesla building their self driving cars.
Every car that Tesla is currently making records 8 different cameras every time that car is driving.
Those video feeds help to train the model Tesla is trying to create for the car to drive itself.
To date Tesla has sold over 575,000 cars since 2014 when they added the cameras needed for self driving.
multiple 575,000 by 8 then multiply that by the number of miles all those cars drive.
It becomes obvious that is just too many video feeds to send over their wireless network
much less to record and store on central servers somewhere.
More importantly, no one wants everywhere they have driven,
and every mistake they made to come back to haunt them.
federated learning allows Tesla to push the model out to their cars.
Let the model be trained by data collected in the car,
then the training corrections are sent back to Tesla without needing to send hours upon hours of video.
Privacy and data bandwidth are preserved.
As a side note, Tesla does upload some video of a car’s driving for things like accidents.
We talk about outliers and making which parts you keep private later.
So, federated learning allows for global results from local data.
Basically train on the local device and send aggregated results back
It allows to keep the sensitive data on device
and if you can promise, and deliver, privacy to the user of an AI model
then you have taken care of one of the biggest fears users have for machine learning.
Think about it, keeping my data private is one of the biggest complaints against people wanting to use AI.
It is right up there with robots taking over the world,
If we can solve real fears now, we can start working on the science fiction fears next.
This is why it is important to UX
All the benefits of privacy for your customers,
plus all the benefits for the company of well trained models.
Of course offering privacy t...
2-David Talby, CTO, Pacific AI
Design for AI
09/11/19 • 34 min
1-Hello! What to expect from ‘Design for AI’
Design for AI
09/04/19 • 10 min
Instead of an interview, the first episode covers what to expect from coming episodes.
Hello and welcome to Design for AI, I’m Mark Bailey. Welcome to episode 1
These podcasts will normally be about interviews and talking about how to address the design problems of machine learning but for the first episode I wanted to talk about what to expect in this podcast.
For those listening who work in this area you are familiar with the current landscape for developing ML is still in the gold-rush stage. There is no one dominant player so a lot of big companies and countries are all trying to competing for any edge possible. The main focus is on getting their app out as quickly as possible. Luckily we are still in the grace period era of new a technology where the capabilities of ML still impress people enough to overlook a whole lot of rough spots.
With all the focus on getting the product out no one is looking at how ML changes the User’s experience. Thats where I come it. So Why me? Well, no one else is. I’ve searched. The podcasts I’ve found so far are talking about the technology side, usually how to develop an AI model there are even some podcasts about the business side of ML. So I’m starting this podcast to talk about design, it is something I find super interesting and I’m surprised No one else is talking about how to make machine learning work better for people.
Well, That is what I hope to accomplish with this podcast anyway. I want to talk to experts in the field to find out how they are dealing with the design challenges of the extra hassles and taking advantage of the extra capabilities that come along with AI.
But I can’t do this alone. I’m going to need your help. Like anything else creative it is better to get started than to get it perfect, I’m an expert in designing software for AI not podcasts so on that note, just like any iterative design. I need your feedback to get better. You, yes I’m talking to you, as the listener, are part of the discussion. I need to know what you are interested in hearing about, what questions do you have? What can I do better? I need you to let me know.
To leave feedback use the voice recorder app on your phone and make sure to give your name then email it to firstname.lastname@example.org
To give a little bit of back story of what my motivation for this podcast is. Years ago when I was working for IBM research, I was really enjoying designing for accessibility because of the extra complexities required to solve some of the universal design puzzles Universal design is no joke when you are trying to design for every group of people of course the deeper you dive the more groups with more and different needs that can compound the problem
or the needs can conflict with each other. Sooner or later, there gets to be too many exception cases to juggle enter machine learning for customizing the UI. Of course, It was early so machine learning didn’t work well but it was enough to peak my interest. I had to teach myself anything user experience related for machine learning. Since all of the attention AI has been on getting the technology better and now the technology is finally getting there.
So who is the Target audience for the podcast? Who do I think will find it interesting? I want to Help the developers who get stuck developing for a ML product without any UX help I want to Help ux designers learn the AI specific problems that are not issues with normal software development cycles. I want to Help PMs know where AI projects can get derailed and what to keep an eye out for. But really anyone interested in ML should find something interesting. I will try to explain any terms I need to any time I need to dive into a more technical area. One caveat is that I use AI and ML interchangeably.
Pretty much every ML development podcast I’ve listened to explains the difference so I’ll leave it to their better explanations.
That leads us to the things we will be talking about.
For the UX designers out there
Trust, how to build it, how to lose it. How AI can help ux processes for better answers. How to improve the jobs you already do as a UX practitioner with AI. How AI affects the GUI in terms of Interaction design. What to look for in user tests to see if the AI is helping or if you are getting users adapting to the test environment. How your user personas affect which models you should build.
For any developers
Special problems AI presents to software development process. What to do when you are designing a chatbot, recommendation system . How to choose the right AI algorithm for a better user experience. How...
17-Chief Strategy Officer at XSENSOR-Murray Vince
Design for AI
03/11/20 • 32 min