Taking Leaps with AI in the Running World

Is it something that we have to be wary of ? What are the differences from using AI to normal training programs , and what other online training resources are there ? So let's go right to the beginning . So what is AI ? Artificial intelligence is a topic that has been discussed in philosophy and science fiction .

It's been a science fiction for decades , but it's rapidly becoming reality . In 2017 , ai became a household name . It was all over the news every day , with companies like Google investing billions of dollars into developing more and more AI applications .

Ai covers some really fascinating topics , from how we design intelligent machines to what our future might look like when these machines are more ubiquitous than humans . But what exactly is it ? What are we so excited about ? Artificial intelligence is a science of making machines that can think like humans . It can do things that are considered smart .

An example might be when Siri tells you when it will rain in your city today . In this part of the podcast , i'll break down some basics of AI so you can better understand what it means in a more simplistic way . What do people really think of AI ? When people are asked about AI , they usually think about Hollywood blockbusters like the Terminator .

It's not surprising when talking to someone who has never heard or has never seen or any mention of artificial intelligence before , often conjured up images similar to those found within movies such as a Terminator , something which most might consider an accurate representation , though .

They think we are at the point where AI can do all things for us Take care of our jobs , make decisions without consulting with humans , and so forth . Now stick with me as I get back to running . I promise I just wanted to give you some background as to what it is . Okay , you're asking , tell me more .

Auto intelligence involves using computers to do things that traditionally require human intelligence . Ai can process large amounts of data in ways that humans cannot . The goal for AI is to be able to do things like recognise patterns , make decisions and judge like humans . To do this , we need lots and lots of data inputted into them .

Ai is the very foundations of some things like image recognition and classification . It's also changing how we make decisions . For example , it can be used to predict traffic light systems or when we get your coffee in the morning . So I hear there is this thing called machine learning .

Well , machine learning or ML is a subset of artificial intelligence as the science of getting computers to learn and act as humans do . In traditional programming and computer is given input data and an algorithm to produce the output .

Now , when I say algorithm , it is basically a function like , for instance , you give me two numbers like two and two , and we use a function , a calculation , to add them together to make four . That's basically what it is in simple terms .

If a computer is given input data with a corresponding output data , so we can learn the algorithm itself and therefore continue to predict the right output data , it is called supervised learning .

Alternatively , if a computer is given a complex set of input data with no corresponding output data , the machine identifies the relationships in the data to provide valuable insights for decision makers . It is called unsupervised learning . Why machine learning is such a big deal . The advent of machine learning has made programming easier .

Before this , programmers had to write instructions to the computers to follow , but if there was a variable that was not on the instructor's instructions , it would stop working . The problem is that technology is used in different ways . There are so many possible things to write rules for that it's not possible To use machine learning .

Programmers can give few basic suggestions to the base rule and then let machines learn from possibilities . Driverless cars are a good example . People don't need to write out instructions to how to deal with every possible thing that could happen involving a pedestrian .

Instead , they can teach the car not to hit pedestrians and provide it with millions of pictures of pedestrians walking near roads . This will help the car know what it needs to do when it sees something similar in the future . So how is machine learning changing our lives ? With machine learning , our computers can finally be more intelligent .

It's not good by itself , so it needs other things to do that . For example , recommendations are powered by machine learning . This is true for recommendations on Google , netflix and Amazon . These same principles also apply to Facebook and Instagram ads . There are now generally viable alternatives for completing complex , time consuming tasks with something other than human .

So what's this thing called chat GPT I keep hearing about ? well , chat GPT is an AI chatbot that uses natural language processing to create human-like conversational dialogue . The language model can respond to questions and compose various written content , including articles , social media posts , essays , code and emails .

Chat GPT is a form of generative AI , a tool that lets users enter prompts to receive human-like images , texts or videos that are created by AI . So chat GPT is similar to the automated chat services found on customer service websites , as people can ask it questions or request clarification to chat GPT replies .

The GPT stands for Generative Pre-Train Transformer , which refers to how chat GPT processes requests and formulates responses . Chat GPT is trained with the reinforcement learning through human feedback and the reward models that rank the best responses . This feedback helps augment and augment chat GPT with machine learning to help improve future responses .

So you created chat GPT . Open AI and an AI research company created and launched the chat GPT in November 2022 . It was founded by a group of entrepreneurs and researchers , including Elon Musk and Sam Altman , in 2015 . Open AI is backed by several investors , with Microsoft being the most notable . Open AI is also created Dow e and AI text to art generator .

So how does chat GPT work ? Chat GPT works by attempting to understand your prompt and then spitting out strings of words that predicts will best answer your question based on the date it was trained on . Let's actually talk about that training .

It's process where the Nancean AI is given some ground rules and then it's either put in situations or given loads of data to work through in order to help develop its own algorithms . Now let's , i know what you're saying . Let's bring it back to running . So I thought you'd I would ask GPT . How is chat GPT useful to runners ?

So it says training and coaching chat GPT can provide personalized training and coaching advice to runners . It can offer guidance on creating training plans , setting goals , structuring workouts based on specific needs and abilities .

The other thing , that said , it said injury prevention , rehabilitation chat GPT can help runners with injury prevention and rehabilitation by providing information on proper running form , exercises for strengthening specific muscles And tips to recovering from common running injuries .

Nutrition and hydration chat GPT can offer insights and recommendations on nutrition and hydration for runners . It can suggest pre and post run meals , discuss the importance of proper hydration and provide guidance on fueling strategies during long distance runs .

Motivation and goal setting chat GPT can serve as a virtual running companion , offer motivation , encouragement , accountability . It can help you set realistic goals , track your progress and provide reminders to stay on track with your training .

Also , race strategy and pacing If you're preparing for a race , chat GPT can help you develop a race strategy based on distance , course and your fitness level . It can provide pacing advice , suggest strategies for tackling hills or adverse weather conditions and offer mental preparation techniques .

Equipment and gear chat GPT can provide recommendations on running shoes , clothing and other gear based on your preferences , budget and running style . It can help you understand the features and benefits of different products to make informed purchasing decisions .

General running knowledge chat GPT can answer a wide range of running related questions , such as the benefits of cross training , the role of rest and recovery , tips of running in different weather conditions and guidance on running etiquette .

It's important to note that , while chat GPT can provide valuable information and support , it doesn't replace the expertise of a qualified coach , trainer and medical professional . For personalized or medical advice , it's always best to consult with a professional who can assess your individual needs and circumstances .

In fact , we will be having a well if you do subscribe to the podcast . We will . We are talking to a running coach professional , so please look out for that episode . So why don't I ask it for a program . This is with . This is the question or message I gave them .

Give me a five kilometer training program for somebody who's best time for the 5K is 33 minutes . They want to be able to do the 5K in 30 minutes . And here's a training , a 5K training program for somebody aiming to approve their time from . This is what it says , from 33 minutes to 30 minutes .

This program spans eight weeks and gradually increases both the mileage and intensity to help you build speed and endurance . Remember to listen to your body , adjust the plan if needed and consult with a healthcare professional before starting any new exercise program . I'll just give you the first couple of weeks So otherwise we'll be here forever .

So week one day one Easy run walk for 20 minutes . Day to rest or cross training . So when it says cross training could be cycling or swimming . Day three interval training warm up with a five minute jog , then do six times 400 meter repeats at a challenging pace . Take a one to two minute recovery walk or jog between each repeat .

Finish with a five minute cooldown jog . Day for rest or cross training Easy run . Day five easy run for 25 minutes . Day six rest and they seven long run walk for 30 minutes . So week two day one easy run for 25 minutes . Day two rest or cross training . Day three a far collect training , which is basically for speed play .

So warm up for five minute jog , then do a five times one minute hard efforts followed by one minute of easy jogging or walking , finished with a five minute called down jog day for rest or cross training . Then day five easy run for 30 minutes . Day six rest . And then on day seven , a long run walk for 35 minutes .

Where this has the advantage compared to other algorithmic , algorithmic , algorithmic training programs , you can add as many variables as you want to your wants and needs . I just asked a very specific basic question with regards to improving my five K time from 33 minutes to 30 minutes .

So I could have said I can only train four times a week , so , or three times a week , so it may give you a longer time frame to accomplish that . There's no guarantees that you will accomplish that . Obviously it depends on you know the effort you put in .

Now I thought I'd do a bit of an experiment and as the same question to a running app and when I use is run keeper , and this is why I came up with . So day one on easy run for three K at six , seven minute pace . Day two easy run for three K at seven minute pace . And then day three is same again .

Day four easy run at three K , seven minute pace . And then again day five easy run , three K , seven minute pace . Day two , little bit different 2.8 kilometer surges intervals , which is between five , 15 to 735 minute pace .

It It would may ask you to do , let's say , a five minute warm up or a four hundred meter warm up , and then you do the , the interval session and a seven arrest . So week two . So week two easy run at a three K at seven minute pace . Day day two again the same date . Day two would be an easy run for five K at seven minute pace .

Day three again the same easy run for five K , seven minute pace . And then day four easy run for three K , a seven minute pace . Then day five easy run , three K , seven minute pace . And then day six , that 2.8 minute , 2.8 kilometer surges , intervals between five , 15 to 735 pace , and then day seven race . So they are very different .

The , the , the app was very specific in terms of pace you had to go . So in summary now with the wrong keeper up , as I said , which is a more algorithmic , function based method , as there are other apps that do the same as one keeper . So ask me how many times a week I wanted to run ? what time did I want to complete it in ?

how many times a week did I want to run ? you know how have I run before And what was my best to last best and my time . For the last time I ran that distance . I've used the app for many years and tweak some of the variables , like not running four times a week and taking it down to three times a week .

There is definitely a pattern , like , for instance , that we can do a gradually increase your long runs . Also , the intervals will start at 3K and then gradually increase to maybe 5K and then maybe you do tempo runs . I suppose you could say that I don't have anything against cats , but there's more than one way to skin a cat .

Then again , there are so many ways to slice and dice whatever It really comes down to what works for you . If you had a personal coach , then they would personally assess you and give you a more tailored programme and be obviously more creative as to the type of training that you would

do . To come to think of it , the major change between the AI programme and Runkeeper is that Runkeeper is an app and it monitors your progress . When you complete your session it knows what you have done , just like the other famous app that counts to 5K .

If you have not met the predetermined mileage for the week , it will change the programme and you have to go back a week , whereas chatGbt is just giving you a template and is not really set in stone . I suppose what I'm saying is that there's no feedback .

For instance , i know when you use the Runkeeper app you're inputting the actual exercise or the session that you've done . Once you've finished for the week , you'll come up with a little badge saying well done , you've completed it for the week , whereas on the , chatgbt is just giving you a template .

I suppose you could put those sessions within , let's say , an app like Strava or even Runkeeper , whatever suits you and whatever your predilection , whatever you feel is more comfortable with you for you . As I said , i've been using the Runkeeper app for quite a while and maybe it might be worth just trying something a little different .

Anyway , i hope I've given you a little bit of a flavour about AI . I thought it would be a good subject to cover , because it is very much in the news . There isn't a day goes by or a week goes by without people talking about it , and just wanted to know as to how it might be useful for people who are starting out their journey in terms of running .

Now I thought we'd come up to a tip

of the week , as I haven't done a tip of the week for quite a while . Again , this is an Apple Watch tip of the week , and this week it'll be a little bit different as well . I'll do a tip also for the Garmin watch and I'll put some links in the show notes for these tips . The Apple Watch tip of the week

is to turn on auto pause . If you don't have the luxury of running in the blissful countryside , it can be very frustrating every time you come across a road and you need to stop . Nice to catch your breath , but not great for the average pace . Auto pause means you don't have to hit that digital crown and side button every time .

You need to pause the clock To turn auto pause on . Open the watch app on your iPhone and head to the My Watch tab From here , tap on Workout and then Auto Pause . You can toggle Auto Pause on and off , which will see your Apple Watch pause when it detects a change in pace and then start again when you get moving

. For Garmin to make the little tip of the week for Garmin your Garmin watch can be very helpful for your intervals . If you're out exercising and you feel like doing intervals , you can easily use the back lap button on the watch .

When the watch is in the process of tracking your run and you press back , your watch will start a new mileage count and you'll want to do 500m intervals . You just need to press the lap back and then , when you complete the 500m , the watch will start a new mileage count .

If you want to gain more control of your intervals , you can also create them before you go in your run on the watch or in the Garmin's Connect .