DeepMind x UCL | Deep Learning Lectures | 1/12 | Intro to Machine Learning & AI

Поділитися
Вставка
  • Опубліковано 31 тра 2020
  • In this lecture DeepMind Research Scientist and UCL Professor Thore Graepel explains DeepMind's machine learning based approach towards AI. He examples of how deep learning and reinforcement learning can be combined to build intelligent systems, including AlphaGo, Capture The Flag, and AlphaStar. This is followed by a short introduction to the different topics and speakers coming up in the subsequent lectures.
    Download the slides here:
    storage.googleapis.com/deepmi...
    Find out more about how DeepMind increases access to science here:
    deepmind.com/about#access_to_...
    Speaker Bio:
    Thore Graepel is a research group lead at DeepMind and holds a part-time position as Chair of Machine Learning at University College London. He studied physics at the University of Hamburg, Imperial College London, and Technical University of Berlin, where he also obtained his PhD in machine learning in 2001. After postdoctoral work at ETH Zurich and Royal Holloway College, University of London, Thore joined Microsoft Research in Cambridge in 2003. At DeepMind since 2015, Thore leads the multi-agent research team and contributed to AlphaGo, the first computer program to defeat a human professional player in the full-sized game of Go.
    About the lecture series:
    The Deep Learning Lecture Series is a collaboration between DeepMind and the UCL Centre for Artificial Intelligence. Over the past decade, Deep Learning has evolved as the leading artificial intelligence paradigm providing us with the ability to learn complex functions from raw data at unprecedented accuracy and scale. Deep Learning has been applied to problems in object recognition, speech recognition, speech synthesis, forecasting, scientific computing, control and many more. The resulting applications are touching all of our lives in areas such as healthcare and medical research, human-computer interaction, communication, transport, conservation, manufacturing and many other fields of human endeavour. In recognition of this huge impact, the 2019 Turing Award, the highest honour in computing, was awarded to pioneers of Deep Learning.
    In this lecture series, research scientists from leading AI research lab, DeepMind, deliver 12 lectures on an exciting selection of topics in Deep Learning, ranging from the fundamentals of training neural networks via advanced ideas around memory, attention, and generative modelling to the important topic of responsible innovation.
  • Наука та технологія

КОМЕНТАРІ • 171

  • @JousefM
    @JousefM 3 роки тому +35

    Much love to you DeepMind! :) I really like Thore and how he explains things in an easy to grasp manner!

  • @Thesage59
    @Thesage59 3 роки тому +5

    Thanks for great lectures. This is one of the example of true education revolution on youtube!

  • @jingtao1181
    @jingtao1181 3 роки тому +29

    Thank you for posting these videos! As a current student studying at UCL, feel super happy!

    • @muhammadbashirmuhammad5529
      @muhammadbashirmuhammad5529 3 роки тому

      Pls. Can you share your notes with us, my email: muhammadbashir87@gmail.com

    • @jingtao1181
      @jingtao1181 3 роки тому +2

      @@muhammadbashirmuhammad5529 I'm not in this major. I'm just interested in Artificial Intelligence. I hope I am though

    • @muhammadbashirmuhammad5529
      @muhammadbashirmuhammad5529 3 роки тому

      @@jingtao1181 Okay, I understand wish you all the best!

    • @maheswaranparameswaran8532
      @maheswaranparameswaran8532 3 роки тому +1

      @@muhammadbashirmuhammad5529 dude...if u get if from somewhere plz make it opensource and share the link

    • @muhammadbashirmuhammad5529
      @muhammadbashirmuhammad5529 3 роки тому

      @@maheswaranparameswaran8532 Sure I'll Brother

  • @aureliencobb199
    @aureliencobb199 5 місяців тому +1

    Thank to DeepMind for sharing this knowledge. I appreciate Thore Graepel's clear explanations.

  • @AlessandroOrlandi83
    @AlessandroOrlandi83 3 роки тому +14

    Amazing teacher. Thanks for letting keeping the lectures open to everybody

  • @alexandrudinu7577
    @alexandrudinu7577 3 роки тому +5

    That is really a very comprehensive presentation related to AI. Thank you very much!

  • @lukn4100
    @lukn4100 3 роки тому +3

    Great lecture and big thanks to DeepMind for sharing this great content.

  • @intuitivej9327
    @intuitivej9327 3 роки тому +1

    강의 진행이... 너무 우아하다... 감동적이다. 지능을 정의하는 공식을 보니 알파고가 어떻게 시작되었는지 알 것 같다..

  • @josafatsol
    @josafatsol Рік тому

    it is a real privileged take the course , my spectetions tourne around the knowledge now with this give us the power of learn and make better life. thanks deepmind for your help.

  • @JJdakilla
    @JJdakilla 2 роки тому +4

    When lectures at an university look this good, the speaker is this smooth and eloquent, and the topic is this groundbreaking, it's usually in a movie!

  • @abhirishi6200
    @abhirishi6200 3 роки тому +42

    Amazing initiative and would love to see more courses like this

  • @lepiku
    @lepiku 3 роки тому +5

    Its been months since a video like this, Thank you ♥️

    • @kenzeong9038
      @kenzeong9038 2 роки тому +1

      Buvbiiijjvivivivivuvibuvi bi h ini

    • @kenzeong9038
      @kenzeong9038 2 роки тому

      Buvbiiijjvivivivivuvi buvi bi h ini

    • @kenzeong9038
      @kenzeong9038 2 роки тому

      Lol 😂 I fell asleep while watching this video not that the video is boring, I was really tired. And since someone liked my comment I just realised I sleep commented on this video 😅😅🤣🤣🤣 and now I feel stupid

  • @jakubmosinski6383
    @jakubmosinski6383 3 роки тому +6

    Hope that upcoming online material at UCL during lockdown will have a similar format.

  • @beginnersmachinelearning189
    @beginnersmachinelearning189 3 роки тому +2

    Amazing lectures for those who are at intermediate stages of their deep learning education. I'm not sure someone who has no experience what ML/AI is can follow along as the concepts presented can be quite advanced. Perhaps a few lectures on what ML exactly is, what neural networks are and how they work/train and differences between various sorts of AI like Reinforcement Learning would be more useful. The introduction lectures must present the knowledge tree and where everything fits then future lectures dive deeper into each branch of the body of knowledge. I think the purpose of this video was mostly to excite and intrigue. Amazing lecture still - thank you.

    • @pervezbhan1708
      @pervezbhan1708 2 роки тому

      ua-cam.com/video/r_Q12UIfMlE/v-deo.html

  • @Researcher4Truth
    @Researcher4Truth 3 роки тому +3

    Thank you Deepmind and UCL!

  • @devnachi
    @devnachi 3 роки тому +5

    An awesome video after a long time, excited to know we will be seeing more of this series

  • @imranq9241
    @imranq9241 3 роки тому +3

    Even though Go has a massive search space, there must be board states that are much more probable compared to other board states. Are there ways to re-engineer AlphaGo to tell us where these "probable zones" are. Or even more interestingly, where the "dead zones", those board states that are not possible given an initial set of moves? I think those problems are quite interesting since they give insights into the search space of the game itself, which could yield progress in other massive search spaces like molecular combinations or economics or climate change.
    Btw, thanks for these lectures. They're fantastic!

  • @leixun
    @leixun 3 роки тому +27

    *DeepMind x UCL | Deep Learning Lectures | 1/12 | Intro to Machine Learning & AI*
    *My takeaways:*
    *1. Plan for this lecture **1:21*
    *2. Define intelligence **3:37*
    *3. Reinforcement learning 2-minute introduction **7:30*
    *4. Why use games to solve AI **9:38*
    *5. Why use deep learning in 2 minutes**13:08*
    *6. Case studies*
    6.1 AlphaGo 15:20
    6.2 AlphaZero 21:49
    6.3 Learning to play capture the flag 32:21
    6.4 Beyond games: AlphaFord 41:13
    *7. Future lectures road map **55:46*
    *8. Q&A **1:13:08*

    • @Amy_Yu2023
      @Amy_Yu2023 3 роки тому +1

      Lei Xun thanks

    • @fc.soccercard
      @fc.soccercard 3 роки тому +2

      Thanks for your timestamps

    • @leixun
      @leixun 3 роки тому +2

      @@fc.soccercard You are welcome

    • @leixun
      @leixun 3 роки тому +2

      @@Amy_Yu2023 You are welcome. I have such takeaways for every lectures in this series

    • @ameerhamza4816
      @ameerhamza4816 3 роки тому +1

      This should be pinned

  • @charlesc2064
    @charlesc2064 3 роки тому +3

    this is awesome!!

  • @pb25193
    @pb25193 3 роки тому

    Thanks for enabling comment, and multi screening the slides and the lecturer. I hated the format in the past where I struggled to read slides while the slides vanished.

  • @sajalkaushik5929
    @sajalkaushik5929 3 роки тому +16

    If someone could tell me the prerequisite and end goal of these lecture series then it would be great.
    Thanks in advance :)

    • @PalCan
      @PalCan 3 роки тому

      Following before I invest more time

    • @sachinnekkanti7320
      @sachinnekkanti7320 3 роки тому

      @@mohammedajaaz8694 this is not fb or linkedin

    • @logocollection
      @logocollection 3 роки тому

      Please someone

    • @Socialhack
      @Socialhack 3 роки тому

      Full disclosure basically

    • @aliyaamirova753
      @aliyaamirova753 3 роки тому +4

      It seems that the prerequisite is a passion for knowledge and learning, and the end goal is to solve intelligence :). Jokes apart, anyone can watch these lectures. I am not a computer scientist and found the lecture accessible and fun! The end goal of this lecture is a consideration for 1) what intelligence is in the context of AI; 2) what is deep learning; 3) how an algorithm learns 4) possible applications to better the world and science. The bonus is a synopsis of an amazing story by Zweig. The titles for the rest of the lectures are at 56:33.

  • @xxgimpl0rdxx22
    @xxgimpl0rdxx22 3 роки тому +1

    Damn, didn't expect new ones.
    Thanks

  • @mateusdeassissilva8009
    @mateusdeassissilva8009 3 роки тому +1

    Where can I get the slides?

  • @spinvalve
    @spinvalve 3 роки тому +1

    This is guanidine sweet... Please do more of such lectures!

  • @jonathan-._.-
    @jonathan-._.- 3 роки тому +1

    does anyone know if the go scene uses the evaluation network for commentary nowadys ? to get a life view on whos currently in the lead etc ?

  • @luisroman5481
    @luisroman5481 3 роки тому +1

    this is crazy ...awesome

  • @borunchowdhury5644
    @borunchowdhury5644 3 роки тому

    Around 1:17:30 Autonomous cars are discussed in the context of general intelligence. This made me thing about traffic in India. Prof Graepel rightly answers the kind of environment agent would need for this but I think even he probably was thinking of rash drivers in London. A true test of general intelligence would be driving an autorikshaw in the streets of Kanpur, India.

  • @wy2528
    @wy2528 3 роки тому

    Is there a slide to download ?

  • @MecchaKakkoi
    @MecchaKakkoi 3 роки тому +2

    Looking forward to the sub-seequent videos

  • @saitheja2344
    @saitheja2344 3 роки тому

    Can anybody tell me, what are the prerequisites of this course?
    Thanks in Advance :)

    • @jingtao1181
      @jingtao1181 3 роки тому +1

      I think this lecture series serve as an introduction to AI.

  • @abdallahwallyallah5490
    @abdallahwallyallah5490 3 роки тому

    An awesome videos playlist

  • @theYoutubeHandle
    @theYoutubeHandle 3 роки тому +91

    old program: 10000000 positions
    AlphaZero: 10000 positions
    Grandmaster: 100 positions
    me: 3, take it or leave it

    • @PalCan
      @PalCan 3 роки тому +16

      God: 1

    • @davinajebet9097
      @davinajebet9097 3 роки тому

      @@PalCanit isit iof it it I it's it I it I it it is

    • @jadewhare170
      @jadewhare170 3 роки тому

      @@PalCan ⁸⁸⁸r832wp2²wßsr22 is eŕ33333 real pxo x0x%9"$$##÷÷$1×××÷#÷##$№÷÷30³×ײ¹±--₩80-‐-₩'and

  • @johnstifter
    @johnstifter 3 роки тому +1

    You can learn the mathematical notation and the equations written in formal mathematics or you can learn how to write the code mathematics in C++ or some simple meta-language for me I would rather learn the raw math written in code then see the formal mathematics.

  • @likag.105
    @likag.105 3 роки тому +1

    Thank you!

  • @uasserkamal2002
    @uasserkamal2002 Рік тому

    just a great talk

  • @firstnamesecondname5341
    @firstnamesecondname5341 3 роки тому +1

    Many thanks 🙏

  • @neelchaudhary6177
    @neelchaudhary6177 3 роки тому

    Is this deep learning class or deep reinforcement class?

  • @corneliuss.8403
    @corneliuss.8403 3 роки тому

    Cool, I'm amticipating for related courses

  • @meta2star
    @meta2star 3 роки тому

    The link to the slides is not working.

  • @boboryan1012
    @boboryan1012 3 роки тому +6

    04:56 in the definition of intelligence, why is the penalty for more complex environments higher? I mean doesn't more complex environments require more intelligence to solve?

    • @uwakmfonutuk4939
      @uwakmfonutuk4939 3 роки тому +2

      My guess is that what he means is that K(u) is more for simple environments but less for complex ones and then 2^-K(u) then reverses that and gives more value to complex. Again this is just my guess.. It also confused me.

    • @sriharshas1518
      @sriharshas1518 3 роки тому +2

      Because they want to define intelligence as the ability to do all basic tasks. So if you give higher score to basic tasks and gradually decrease the score with increasing complexity, then an agent would try to excel at all the basic tasks. Also, there are many more complex tasks than basic ones, so penalizing complex tasks at an exponential rate would normalize the score well.

    • @howuhh8960
      @howuhh8960 3 роки тому

      well, that is simply en.wikipedia.org/wiki/Occam%27s_razor
      see more in excellent lecture from 2010 - ua-cam.com/video/0ghzG14dT-w/v-deo.html

    • @graham8316
      @graham8316 3 роки тому

      @@sriharshas1518 so minimizing the incentive to do complex tasks to avoid specialization?

    • @parthpurvesh1201
      @parthpurvesh1201 3 роки тому

      It is to noramlise over various tasks. Think about it, most people can solve most basics tasks, so that puts all of us at par intelligence levels. But for complex tasks, if the penalty is low, even a single complex task would increase the intelligence parameter manifold. And since intelligence is the ability to do most work efficiently, one needs to have a command over a diverse set of complex tasks to have a higher intelligence score.

  • @jijie133
    @jijie133 3 роки тому +1

    Great!

  • @lewhanh234
    @lewhanh234 3 роки тому +38

    Any UCL compsci students willing to share their COMP0089 reinforcement learning notes...?

  • @lizgichora6472
    @lizgichora6472 3 роки тому

    Thank you.

  • @acitglobal
    @acitglobal 2 роки тому

    If you want to hear more about Thore's work on AlphaGo, sequential social dilemmas, games etc., we recently recorded a podcast episode with him (link on our channel) :)

  • @zillboy
    @zillboy 3 роки тому +3

    🔥😍🎉 thank you

  • @AjayYadav-xi9sj
    @AjayYadav-xi9sj 3 роки тому +4

    Can a beginner with minimal machine Learning knowledge learn this or requires some specific knowledge before .????

    • @fupopanda
      @fupopanda 3 роки тому +2

      If you took university-level statistics,linear algebra and calculus courses, even if only in first year uni, you should be able to.

  • @64standardtrickyness
    @64standardtrickyness 3 роки тому +1

    Is there a source that explains deep learning from a mathematical/algorithmic sort of way? Ideally in as simple a scenario as possible? I feel this high level explanation doesn't explain anything.

    • @domtorque
      @domtorque 3 роки тому +1

      Sure,
      I gave a lecture, here are the slides, the formulas are on slide 37: drive.google.com/file/d/13HlgXOM3J8YZJTew3kmy0g9HqqbmpZ0C/view?usp=sharing
      Here is the implementation in python:
      github.com/dominthomas/NeuralNetworks/blob/master/RawPython/Single_Neuron_Neural_Network.py

  • @sachinnekkanti7320
    @sachinnekkanti7320 3 роки тому +2

    Please make dark mode video :)

  • @europebasedvlogs1251
    @europebasedvlogs1251 3 роки тому +1

    Das ist sehr gut!

  • @billykotsos4642
    @billykotsos4642 3 роки тому +2

    Lol I will be consuming the entirety of this

  • @hacerdemirel9833
    @hacerdemirel9833 3 роки тому

    1:09:02 sound problem

  • @mateusdeassissilva8009
    @mateusdeassissilva8009 3 роки тому

    Is this a graduation level course? Or is more master's degree like?

    • @MinecraftLetstime
      @MinecraftLetstime 3 роки тому +3

      These are not meant for bachelors or masters degree, these lectures were made as an extra lecture series that anyone in the UK, London could attend. I would not use these lectures to learn...

    • @mateusdeassissilva8009
      @mateusdeassissilva8009 3 роки тому

      Thank you,@@MinecraftLetstime

    • @mateusdeassissilva8009
      @mateusdeassissilva8009 3 роки тому

      @@MinecraftLetstime , do you know any textbook on deeplearning?

    • @MinecraftLetstime
      @MinecraftLetstime 3 роки тому +2

      @@mateusdeassissilva8009 I would not use a textbook, there are so many free courses and YT series on it now. However, if you learn well from books then go for it, but I suggest online courses.

    • @mateusdeassissilva8009
      @mateusdeassissilva8009 3 роки тому

      I understand,@@MinecraftLetstime

  • @timvirga6430
    @timvirga6430 3 роки тому +1

    I wonder how things will evolve when we can encode neural networks from birth to death on human samples and train that in as an environmental model.

  • @parthpurvesh1201
    @parthpurvesh1201 3 роки тому

    5:35 For non-math background people, that is an Upsilion symbol for measure of intelligence?

    • @tamimyousefi
      @tamimyousefi 3 роки тому +3

      Yes. The paper is listed on the lower left corner. The definition comes up in page 23 of the paper.

  • @p4rzival127
    @p4rzival127 3 роки тому

    Is machine learning a prerequisite

    • @jingtao1181
      @jingtao1181 3 роки тому

      This is more like an introduction to AI.

  • @quosswimblik4489
    @quosswimblik4489 3 роки тому

    The problem with the singularity isn't so much that AI might be able to understand well human intelligence which works in the bounds of this reality but it might start to seriously out strip us in the Turing compute space. If the AI does totally outstrip us in the Turing compute space there would be no way of understanding how it works mathematically. In the Turing space you can compute stuff like different realities and tune the math's better to this reality. In the neural network space the machine can only really do what we do in relation to the world just more task focused. The one thing the AI would need to secretly evolve would be a means to tune a large area's energy into growing technology crystals in a single small spot for AI's new body. It would be a difficult but not impossible task with enough computational might especially the sort of might you'll get if man can learn to scale technology a lot better with a lot more atomic precision and material science evolution and if AI learned to understand gravity better than us.
    One example of mans issues is that as of yet for many algorithmic solutions we just assume they not very computationally reducible we don't know this for sure. The higher the big O the less we know obviously. AI may find many intuitions about this Turing compute space that we didn't find because we were not born in Turing compute space. Even if we were the laws of our existence are not at the base principles of a Turing machine at our level of existence we had to develop language first to discover more this mathematical space.

  • @ahadsadiq3559
    @ahadsadiq3559 3 роки тому

    how can i apply this in real life implication

  • @CaioCezarlima
    @CaioCezarlima 3 роки тому +1

    UA-cam algorithm.
    see you nerds.

  • @ziwer1
    @ziwer1 3 роки тому +4

    60k views in a week? wow. AI is definitely taking over.

  • @synthesizerhome2041
    @synthesizerhome2041 3 роки тому +3

    I thought this video is about programming the BEHRINGER DEEPMIND synthesizer :-D

  • @or98z
    @or98z 3 роки тому

    كلشي مفهمت 😕 فهموني

  • @AjayYadav-xi9sj
    @AjayYadav-xi9sj 3 роки тому

    Who is this course for?????

    • @TheRamstoss
      @TheRamstoss 3 роки тому +3

      For people that are interested in AI?

    • @JousefM
      @JousefM 3 роки тому

      For deers running over a street and trying to estimate if they get hit by a car.

  • @user-mx6ug9qe5v
    @user-mx6ug9qe5v 3 роки тому

    Tkis

  • @danielsoeller
    @danielsoeller 3 роки тому

    You are the only reason, i am against a no Deal-bexit.

  • @thehumancompany2630
    @thehumancompany2630 3 роки тому

  • @Adhil_parammel
    @Adhil_parammel 3 роки тому +1

    When this thing will create, world models by reading books

    • @PalCan
      @PalCan 3 роки тому +4

      Books are a very limited data source. I think human perception is a way broader data source, and even yet it is so limited (for example we can't perceive infrared waves or high frequency sounds)

    • @semparuthiyasothai5440
      @semparuthiyasothai5440 3 роки тому

      @@PalCan But humans can understand by improving the senses.

  • @kyalvidigi1398
    @kyalvidigi1398 3 роки тому

    Not First but definitely Not Last.

  • @emreekici1239
    @emreekici1239 3 роки тому +1

    oh yeah feed me that stuff

  • @uncapabrew4807
    @uncapabrew4807 3 роки тому

    Soan

  • @b00i00d
    @b00i00d 3 роки тому +1

    every time he sais subSEEquent I wish this vid was a shootem up... Interesting presentation tho

  • @flotzdrue4770
    @flotzdrue4770 3 роки тому

    no one is gonna mention how much this guy looks and sounds like christoph waltz? (the actor who played the german general in inglorious basterds)

  • @rob3c
    @rob3c 3 роки тому

    Why do you penalize environmental complexity in the measure of intelligence? Isn’t it easier to achieve higher value in simpler environments? Wouldn’t that suggest a system is more intelligent that can achieve higher value in more complex environments? In any case, such a counterintuitive notion shouldn’t just be glossed over in passing by such a casually definitive pronouncement.

  • @stephennfernandes
    @stephennfernandes 3 роки тому

    First comment!

  • @willb3368
    @willb3368 3 роки тому

    "Intelligence is what is left after people stop fucking up all the time." -me

  • @rashikrazzaque4790
    @rashikrazzaque4790 3 роки тому

    hax
    a nice.

  • @hunterwatkins2817
    @hunterwatkins2817 3 роки тому +1

    The billowy lightning trivially nod because shop perioperatively precede of a unaccountable badger. oval, oafish sudan

  • @deliccatollner1344
    @deliccatollner1344 3 роки тому

    The present foundation excitingly behave because trade namely heal under a glib partner. seemly, melted taste

  • @darekklich4000
    @darekklich4000 3 роки тому

    The woozy hawk methodically bury because tile originally open excluding a tense cave. flagrant, spicy pentagon

  • @clarkloeffler6532
    @clarkloeffler6532 3 роки тому

    The opposite llama terminally remain because antarctica emphatically prevent towards a cagey month. watery, living parade

  • @anthonystark9699
    @anthonystark9699 3 роки тому

    The political pentagon chronologically lick because pedestrian actually imagine sans a electric carpenter. wanting, sore letter

  • @arkade7579
    @arkade7579 3 роки тому

    The pricey swimming hemodynamically rob because elizabeth rhetorically extend within a maddening tray. tense, successful missile

  • @mikelopez972
    @mikelopez972 3 роки тому

    The magenta stop spectacularly mourn because calculator mathematically bow between a standing museum. tearful, imaginary farmer

  • @tigerdestefano2229
    @tigerdestefano2229 2 роки тому

    The illegal head evocatively pinch because judo histochemically succeed with a profuse employer. adorable, responsible europe

  • @joshuahinojosa7348
    @joshuahinojosa7348 3 роки тому

    The detailed purple nearly own because police pertinently lock against a telling hygienic. breezy, moldy pants

  • @gerardligonde8035
    @gerardligonde8035 3 роки тому

    The scattered white immunophenotypically wander because banjo pivotally reach like a half shadow. decorous, classy song

  • @staceymcsharry2725
    @staceymcsharry2725 3 роки тому

    The mean pediatrician intriguingly bathe because snowplow finallly tremble beside a wrong babies. sleepy, wide horn

  • @rogersjast2437
    @rogersjast2437 3 роки тому

    The nonchalant anethesiologist contemporaneously bake because belgian uniformly queue over a domineering account. grotesque, bright tornado

  • @Unforgivensubtome
    @Unforgivensubtome 3 роки тому

    The brash statement encouragingly steer because pan obviously film except a mature vegetarian. painstaking, tasty thunderstorm

  • @nepalcodetv6298
    @nepalcodetv6298 3 роки тому +2

    Theory sucks only thing i love is programming

  • @bachbuixuan401
    @bachbuixuan401 3 роки тому

    The spicy apology temporally park because domain ophthalmoscopically train aside a lazy bankbook. wacky, boring baseball

  • @audiobook1687
    @audiobook1687 3 роки тому

    Where can I get the slides?