Ready to become a certified watsonx Data Scientist? Register now and use code IBMTechYT20 for 20% off of your exam → https://ibm.biz/Bdpij5 Learn more about Linear Algebra for Machine Learning here → https://ibm.biz/BdpijN How do machines learn to recognize cats and dogs in images? 🐾 Fangfang Lee explains how linear algebra powers machine learning, from vectors and matrices to SVD and cosine similarity. Learn how these concepts transform raw data into actionable intelligence for AI and neural networks! AI news moves fast. Sign up for a monthly newsletter for AI updates from IBM → https://ibm.biz/Bdpij7 #machinelearning #linearalgebra #aiconcepts
ADVERTISEMENT
6:06 - there’s a minor mistake here. ie. The COS of two vectors “pointing in the exact same direction” = +1. Very good video overall !
Other than the cosibe mistake, this video has been really insightful and informative to me. Thanks!
Everyone at IBM is left-handed apparently.
Great
Does all of this math allow them to code human voice inflection as well? I would guess that would help identifying context. Or is that a limitation that hinders reason?
Very simple concise demonstration.
Thank you very much, learned new data types.
Thank you for the great content!
I enjoyed the video, very insightful! However, what puzzled me is that you are mentally reversing what you write on the glass, what kind of model would we call that, hahaha.
Loved this video, keep up the great work!
Row or column? You said or used it opposite.
Very well done, appreciate this video!
This was super helpful, thanks!
Correlation doesn’t imply independence, unless variables are normally distributed
6:06 - I suddenly began to rethink my entire existence... 6:41 - ... drew me back to life
Great tips, thanks for sharing!
Thanks Algebra Teacher Liezl :)
I think around minute 6, the additive vectors should be 1, not -1?
That was more algebra concepts than tensor application 😅
I can't believe these lectures are available freely w/o any type of sign up