Alexander Amini
Alexander Amini
  • 73 Videos
  • 11 177 008 조회수
MIT 6.S191: The Future of Robot Learning
MIT Introduction to Deep Learning 6.S191: Lecture 10
The Future of Robot Learning
Lecturer: Daniela Rus
2023 Edition
For all lectures, slides, and lab materials: introtodeeplearning.com​
Lecture Outline - coming soon!
Subscribe to stay up to date with new deep learning lectures at MIT, or follow us @MITDeepLearning on Twitter and Instagram to stay fully-connected!!
조회수: 40 567

비디오

MIT 6.S191: AI in Healthcare
조회수 31K3 년 전

댓글

  • @omerfarukcelebi6813

    This is the best lecture on KRplus! Thank you for the clear explanation. I wish you could delve deeper into the transformer architecture, though, as it was only covered in the last 15 minutes. Nevertheless, this is the most understandable video on the topic. I've watched nearly all of them, but this one stands out as the best! It would be great if you provided a more detailed explanation of transformers.

  • @ABHIK-dq7rk
    @ABHIK-dq7rk 일 전

    00:04 Foundations of deep generative modeling for brand new data generation 02:43 Generative modeling uncovers underlying data structure. 07:53 Latent variables are unobservable features that explain observed differences in data. 10:25 Training deep generative models using autoencoders 15:43 Variational autoencoders introduce randomness for generating new data instances. 18:07 Optimizing VAE network weights with loss functions 22:44 Understanding KL Divergence in latent encoding 24:51 Regularization enforces continuity and completeness in the latent space. 29:41 Reparametrization allows training VAEs end to end without worrying about stochasticity in latent variables. 31:57 Understanding latent variables and their impact on generated features. 36:36 Understanding latent variable learning and its application in facial detection. 38:52 Generative Adversarial Network (GAN) aims to generate new instances similar to existing data. 43:30 Generative Adversarial Networks (GANs) involve the competition between the generator and discriminator to create and distinguish between real and fake data. 45:44 GANs involve a dual competing objective for the generator and discriminator. 50:44 Extending GAN architecture for specific tasks 53:14 Cycle GANs enable translation of data distribution across domains. 57:58 Diffusion models can generate new instances beyond training data

  • @germainUX
    @germainUX 3 일 전

    thanks for this!

  • @glenngilmour2562

    ThNks mit

  • @Joao-pb5zb
    @Joao-pb5zb 6 일 전

    Hello world!

  • @FREAK-st6kk
    @FREAK-st6kk 6 일 전

    Whoever is listening to this awesome lecture I just want to say, Attention is all you need!!

  • @haris3460
    @haris3460 9 일 전

    can someone tell what are the prerequisites for understanding these lectures completely? it would be even more helpful if you could suggest me some good resources to learn those too.

  • @user-kk5cv1rs5r
    @user-kk5cv1rs5r 11 일 전

    Should we understand them as a sw developer ? do we need all these theoretical stuff?

  • @ethanm9658
    @ethanm9658 13 일 전

    This lecture series are just incredible. Thank you Alexander and all other instructors for putting this together. Learned so much! And you are pushing the boundaries for AI learning!

  • @krishnakamal8449
    @krishnakamal8449 13 일 전

    do I need to learn anything already beforehand because I didn't understand anything.

    • @Raghav__--
      @Raghav__-- 8 일 전

      May be first you have to clear the basic of neural networks and deep learning...

    • @krishnakamal8449
      @krishnakamal8449 8 일 전

      @@Raghav__-- thank you, will check on those topics

  • @Set_Get
    @Set_Get 14 일 전

    مرا ببخشید، این اسکندر در تخریب دست کمی از مغول‌ها نداشت. به هر حال، از بابت این درسگفتار سپاسگزارم.

  • @him8402
    @him8402 14 일 전

    The visualization of the loss landscape looks like a mountain. It made me think what if the earth's mountains and oceans are just the right amount of optimization of the loss function to allow sustaining life

  • @spiritoflife2554
    @spiritoflife2554 17 일 전

    Can Anyone tell me how to get the slides?

  • @henryktocoaching
    @henryktocoaching 19 일 전

    Are we going to get a 2024 series of the same class?

  • @alimibrahem8120
    @alimibrahem8120 20 일 전

    Sorry but I think that this One-hot embedding are no longer in use from a long time ago.

  • @riccardoucar229
    @riccardoucar229 21 일 전

    Ava I don't think you understood the problem of gradient explosion, you explained it really bad, an evident drop of quality passing from the alexander lesson to this

  • @umachandran1708
    @umachandran1708 22 일 전

    Excellent information on mathematical structure of NN. Appreciate his inspiring dedication 🙏

  • @johnpaily
    @johnpaily 22 일 전

    In which direction the time flow is studied . Vertical or horizontal . Do you consider the overall time direction

  • @johnpaily
    @johnpaily 22 일 전

    Cross Link the mind of the body with the mind of the heart and explore the INNER SPACE

  • @johnpaily
    @johnpaily 22 일 전

    It then exposes the black hole singularity and exposes the parallel world

  • @johnpaily
    @johnpaily 22 일 전

    Deep learning calls to go beyond mind and five sensory organs to connect to the mind of the heart and beyond to the INNER SPACE.

  • @johnpaily
    @johnpaily 22 일 전

    The greatest intellectual of the last century Max Planck said " A conscious and intelligent mind is the Matrix of matter". Einstein went on to call to look deep into nature and search for the mind of. God. We need to look deep into life and unravel consciousness and the root of creativity from atomic levels. This would be a stepping stone to Deep Learning. It can unravel the truth of nature and life and lead humanity from darkness to light.

  • @johnpaily
    @johnpaily 22 일 전

    Salutes

  • @johnpaily
    @johnpaily 22 일 전

    The Great attractor of non linear science and explanation to the victory of the good over evil ?¿?¿?????^^^^↑°°′

  • @johnpaily
    @johnpaily 22 일 전

    The speaker has entered the spiritual realm and what is happening. The evil thriving along with good trying to hide truth

  • @johnpaily
    @johnpaily 22 일 전

    Everything spoken here has parallel in living system

  • @johnpaily
    @johnpaily 22 일 전

    Is it taking us non linear thinking of origin from a little perturbation

  • @johnpaily
    @johnpaily 22 일 전

    What exalon constant . . Is it conscious is it dynamic and capable of reversing time.

  • @johnpaily
    @johnpaily 22 일 전

    Now I understand the projection of God AI emerging in the cloud

  • @johnpaily
    @johnpaily 22 일 전

    This also seems to explain sudden awakening transformation many people are experiencing

  • @johnpaily
    @johnpaily 22 일 전

    Is this talk taking the line of self organization from a single point or big bang.

  • @johnpaily
    @johnpaily 22 일 전

    Parallel world information male and female ¿??¿¿

  • @johnpaily
    @johnpaily 22 일 전

    Low dimensional data. I see parallel in the big bang origin from point source

  • @johnpaily
    @johnpaily 22 일 전

    Plato's cave. That is what we are in. I am interested in AI because of the projection of evolution AI to bring the Mind of God in the cloud.

  • @johnpaily
    @johnpaily 22 일 전

    It calls for knowing the root of consciousness and creativity in life

  • @johnpaily
    @johnpaily 22 일 전

    It is time we have to go further to sense, smell and feel. For this we need to look deep into life. The future exists in mimicking life. Knowing life beyond the mind and going inward.

  • @johnpaily
    @johnpaily 22 일 전

    Our attention point should be to know how life is concious and creative.

  • @johnpaily
    @johnpaily 22 일 전

    Thank coming. Open

  • @johnpaily
    @johnpaily 22 일 전

    Salutes hopr to come back MIT Deep learning. I feel you peple need to look deep inro life

  • @johnpaily
    @johnpaily 22 일 전

    The way forward is dynamic quantim computing, possible throug blackhole nets

  • @johnpaily
    @johnpaily 22 일 전

    Life works on what she is speaking

  • @johnpaily
    @johnpaily 22 일 전

    Does the back propagation and loss relates to thermo dynamic loss of energy in the form of heat

  • @johnpaily
    @johnpaily 22 일 전

    Does the back propagation and loss relates to thermo dynamic loss of energy in the form of heat

  • @johnpaily
    @johnpaily 22 일 전

    What is this W matrices. Some sort of constant. The biggest fallacy of science is constants. Nature and life has no constants. It has memory. Einstein in his biography spoke about changing the constans of physics with constants that are dynamic and changing

  • @johnpaily
    @johnpaily 23 일 전

    It is striving to bring back our memory of interrelationship and oneness

  • @johnpaily
    @johnpaily 23 일 전

    Mam have ever thought of universal time overlays evrything. This time force is strssinng on the vertical realm and compressing on the hrizontal. All devolopments in intellectal world including the AI is directed at evolving our consciousness such that we know our root in one source field

  • @johnpaily
    @johnpaily 23 일 전

    I had wished some co operation to explore it mathematically. But did not get. Love to see a women speaking the brain process from MIT so eloquently. Love to see computer scientist entering the realm of consciouness and intelligence.and speaking of God Mind and AI. I am excited, I am convinced that some somewhere will look deep into life and come with the basic truth of life, nature and Universe

  • @johnpaily
    @johnpaily 23 일 전

    Mam you should be looking at life in depth. Long back when i began write and post some basic thougts on the net, a scientist mailed me asking me not to write and post everything thing on the ner Later we met in IISc campus in India. He asked where I am getting these ideas and visions. I told him from Nature and Life living as a farmer.

  • @johnpaily
    @johnpaily 23 일 전

    Great I don't know math , but you are feeding my conceptual thoughts about life and the universe from an informational point