Moore's Law Is Ending... So, What's Next?

00:04:20
https://www.youtube.com/watch?v=Vv_2C95cO6s

Résumé

TLDRDie video ondersoek die ontwikkeling van slimfone vanaf hul eenvoudige begin, met beperkte geheue, tot die moderne tegnologie aangedryf deur Moore se Wet. Dit stel voor dat die aantal transistors in 'n geïntegreerde stroombaan elke twee jaar verdubbel, wat gelei het tot baie kragtiger en kleiner toestelle. Maar hierdie vooruitgang staar uitdagings van vertragings in miniaturisering in die gesig. Nuwe tegnologieë soos kwantum- en neuromorfiese rekenaars kom in die prentjie. Neuromorfiese rekenaars boot die strukture van die menslike brein na en kan rekenaars in staat stel om te leer en te besluit. Dit kan 'n toekoms bied met robots en slim voertuie wat in staat is tot komplekse besluitnemingsprosesse in werklike tyd.

A retenir

  • 📞 Onthou hoe cellfone eers was?
  • 📈 Moore se Wet is die basis van tegnologiese vooruitgang.
  • 🔬 Neuromorfiese rekenaars boot die menslike brein na.
  • ⚙️ Neuromorfiese chips kan hervorm hoe ons rekenaars gebruik.
  • 🤖 Toepassings sluit robots en selfbestuurde motors in.
  • 🧠 Neuromorfiese tegnologie kan rekenaars in staat stel om te leer.
  • 🔄 Moore se Wet laat ons telefonies verbeter.
  • 🔋 Mos transistors maak kragtiger toestelle moontlik.
  • 🚀 'n Toekoms met intelligente en leergierige masjiene is op pad.
  • 📺 Seeker VR bied 'n ander ervaring vir verkenning.

Chronologie

  • 00:00:00 - 00:04:20

    In die vroeë dae het selfone 'n beperkte kapasiteit gehad, maar deur die jare het tegnologie voortgegaan om vinniger en meer gevorderd te word volgens Moore se Wet. Hierdie wet voorspelling dat die aantal transistors in 'n geïntegreerde stroombaan elke twee jaar sal verdubbel terwyl die koste halveer, het gelei tot byna onbeperkte rekenaarkrag in ons fone. Moderne chips bevat miljarde transistors, en die gesprek dryf die ontwikkeling in 'n tyd wanneer die genetiese teenwoordigheid al hoe moeiliker word. As gevolg hiervan word nuwe benaderings soos kwantum rekenaars en neuromorfiese rekenaars ondersoek. Neuromorfiese chips volg die model van die menslike brein, en kan geheue, berekening en kommunikasie op 'n nuwe manier integreer. Hierdie tegnologie kan rekenaars transformeer in intellektuele masjiene wat van ervaring kan leer en besluite kan neem, wat lei tot 'n toekoms waar ons robots met 'n brein agter hulle het.

Carte mentale

Vidéo Q&R

  • Wat is Moore se Wet?

    Moore se Wet stel dat die aantal transistors in 'n geïntegreerde stroombaan elke twee jaar sal verdubbel terwyl die koste halveer.

  • Wat is neuromorfiese rekenaars?

    Neuromorfiese rekenaars is chips wat gemodelleer is na menslike breine en in staat is om te leer en te onthou.

  • Hoe werk neuromorfiese chips?

    Neuromorfiese chips gebruik 'n netwerk van transistors wat die werking van ionkanale in neurone naboots, wat hulle in staat stel om geheue, berekening en kommunikasie te integreer.

  • Wat is die potensiële toepassings van neuromorfiese chips?

    Hulle kan gebruik word in gevegrobots, drones wat omgewingsveranderinge kan opspoor, en selfs in selfbesturende motors.

  • Hoe verskil neuromorfiese rekenaars van huidige rekenaars?

    Neuromorfiese rekenaars verbind geheue en verwerking binne die 'neurone', in teenstelling met die tradisionele von Neumann-argitektuur.

Voir plus de résumés vidéo

Accédez instantanément à des résumés vidéo gratuits sur YouTube grâce à l'IA !
Sous-titres
en
Défilement automatique:
  • 00:00:00
    Remember when cellphones looked like this?
  • 00:00:02
    You could call, text, maybe play snake on it … and it had about 6 megabytes of memory,
  • 00:00:07
    which was a small miracle at the time.
  • 00:00:10
    Then, phones got faster and around every two years, you probably upgraded your phone from
  • 00:00:15
    8 gigs to 16 to 32 and so on and so forth.
  • 00:00:19
    This incremental technological progress we’ve all been participating in for years hinges
  • 00:00:22
    on one key trend, called Moore’s Law.
  • 00:00:25
    Co-founder of Intel, Gordon Moore made a prediction in 1965 that integrated circuits, or chips,
  • 00:00:32
    were the path to cheaper electronics.
  • 00:00:34
    Moore’s law states that the number of transistors, the tiny switches that control the flow of
  • 00:00:39
    an electrical current that can fit in an integrated circuit, will double every two years, while
  • 00:00:45
    the cost will halve.
  • 00:00:47
    Chip power goes up as cost goes down.
  • 00:00:50
    That exponential growth has brought massive advances in computing power… hence tiny
  • 00:00:54
    computers in our pockets!
  • 00:00:57
    A single chip today can contain billions of transistors, and each transistor is about
  • 00:01:02
    14 nanometres across!
  • 00:01:04
    That’s smaller than most human viruses!
  • 00:01:06
    Now, Moore’s law isn’t a law of physics, it’s just a good hunch that’s driven companies
  • 00:01:12
    to make better chips.
  • 00:01:15
    But experts are claiming that this trend is slowing down.
  • 00:01:18
    Granddaddy chip maker Intel recently disclosed that it's becoming more difficult to roll
  • 00:01:23
    out smaller transistors in a two year timeframe while also being affordable.
  • 00:01:28
    So, to power the next wave of electronics, there are a few promising options in the works.
  • 00:01:32
    One is quantum computing.
  • 00:01:35
    Another currently in the lab stage is neuromorphic computing, which are computer chips that are
  • 00:01:40
    modeled after our own brains!
  • 00:01:41
    They’re basically capable of learning and remembering all at the same time at an incredibly
  • 00:01:45
    fast clip.
  • 00:01:47
    Let’s break that down and start with the human brain.
  • 00:01:49
    So, your brain has billions of neurons, each of which forms synapses or connections with
  • 00:01:55
    other neurons.
  • 00:01:56
    Synaptic activity relies on ion channels, which control the flow of charged atoms like
  • 00:02:01
    sodium and calcium that make your brain function and process properly.
  • 00:02:04
    So, a neuromorphic chip copies that model by relying on a densely connected web of transistors
  • 00:02:10
    that mimic the activity of ion channels.
  • 00:02:13
    Each chip has a network of cores, with inputs and outputs that are wired to additional cores,
  • 00:02:19
    which all operate in conjunction with each other.
  • 00:02:22
    Because of this connectivity, neuromorphic chips are able to integrate memory, computation,
  • 00:02:27
    and communication all together.
  • 00:02:29
    These chips are an entirely new computational design.
  • 00:02:32
    Standard chips today are built based on von Neumann architecture...
  • 00:02:36
    where the processor and memory are separate and the data moves between them.
  • 00:02:41
    A central processing unit runs commands that are fetched from memory to execute tasks.
  • 00:02:46
    This is what’s made computers very good at computing, but not as efficiently as they
  • 00:02:50
    could be.
  • 00:02:51
    Neuromorphic chips however completely change that model by having both storage and processing
  • 00:02:55
    connected within these “neurons” that are all communicating and learning together.
  • 00:02:59
    The hope is that these neuromorphic chips could transform computers from general purpose
  • 00:03:04
    calculators into machines that can learn from experience and make decisions.
  • 00:03:09
    We'd leap to a future where computers wouldn't just be able to crunch data at break neck
  • 00:03:13
    speeds but could do that AND process sensory data in real time.
  • 00:03:18
    Some future applications of neuromorphic chips might include combat robots that could decide
  • 00:03:23
    how to act in the field, drones that could detect changes in the environment, and your
  • 00:03:27
    car taking you to a drive through for ice cream after being dumped…
  • 00:03:33
    basically these chips could power our future robot overlords.
  • 00:03:36
    We don't have machines with sophisticated, brain-like chips yet but they’re on the
  • 00:03:40
    horizon.
  • 00:03:41
    So get ready for a whole new meaning for the term “brain power.”
  • 00:03:44
    But we have something less frightening than AI to share with you... did you know we have
  • 00:03:47
    a sister channel called Seeker VR?
  • 00:03:49
    It’s everything you love about Seeker, but in 360 degrees!
  • 00:03:53
    SeekerVR will take you on some incredible journeys that you probably wouldn’t get
  • 00:03:56
    to experience otherwise.
  • 00:03:57
    Like in a recent episode, we took a ride on one of the most deadly trains in the world.
  • 00:04:03
    Check it out here.
  • 00:04:04
    Want to learn more about how the fastest computers in the world work?
  • 00:04:08
    We’ve got a video about them here.
  • 00:04:09
    And am I the only one who misses my Motorola Razr?
  • 00:04:13
    Let us know in the comments and check back here for more videos.
Tags
  • Moore se Wet
  • slimfone
  • neuro-informatika
  • kwantumrekenaars
  • tegnologiese vooruitgang
  • menselike brein
  • gevegrobots
  • selfbestuurde motors
  • uitvindinge
  • entiteit van chips