Yes, unsupervised learning! We have taught too much on classification, regression, SVM, ANN, that focus on supervised learning. Our brains are sub/un-consciously learning about the environment continuously, i.e. doing unsupervised learning.
Mr Ng has an interesting pattern in his own speech... starting a sentence in a clear strong audio, and fading to a silent muted tone at the end of a sentence. :) (makes it difficult to hear the complete statement sometimes )
Usually by an iterative process that first finds a set of basis vectors that sparse represent the current set of observations (images), and then finds new sparse representations (the alphas) using that set of basis functions. Rise and repeat.
This has been flagged as spam show
Awesome lecture
kuangjinjun 4 weeks ago
Yes, unsupervised learning! We have taught too much on classification, regression, SVM, ANN, that focus on supervised learning. Our brains are sub/un-consciously learning about the environment continuously, i.e. doing unsupervised learning.
leverwang 1 month ago
Mr Ng has an interesting pattern in his own speech... starting a sentence in a clear strong audio, and fading to a silent muted tone at the end of a sentence. :) (makes it difficult to hear the complete statement sometimes )
razblack 1 month ago
Andrew Ng is the best professor I've ever had the privilege to learn from (ml class).
fingerprint211b 2 months ago 4
guys dont forget his free online Machine Learning class starting in January.
Funtasmia 2 months ago 2
andrew a great machine learning scienctist
ahmedgalcaio 2 months ago
napakaganda ng video! another one from google
adelle0001 3 months ago
REALLY VERY GOOD VIDEO
artificialintellige1 4 months ago
amazing!
mehdigoudarzi 4 months ago
Usually by an iterative process that first finds a set of basis vectors that sparse represent the current set of observations (images), and then finds new sparse representations (the alphas) using that set of basis functions. Rise and repeat.
amadananl 6 months ago
i don't get how the phi basis functions at 13:00 are derived?
matpalmyt 8 months ago
@matpalmyt neither do I D:
alfaalfa99 3 months ago
Awesome lecture
cijojose1 8 months ago
Fantastic lecture!
wblnumber1 8 months ago
This talk is awesome; I can quickly pick up key points of deep-learning.
lei07fun 10 months ago 10
Andrew Ng got bored of improving one algorithm so he decided to improve all algorithms at once...
Mangalaiii 10 months ago 54
i envy people living in the bay area.
-M
Redmond (just kidding)
beardymonger 10 months ago
Intriguing ideas.
malusmoriendumest 10 months ago
If you are interested in Machine learning, see Stanford's Machine Learning Course, here on youtube by the same speaker Andrew Ng
SalsaTiger83 10 months ago 6
Excellent video, very informative and didactic
paucarre 10 months ago