Gradient Descent Explained

Gradient descent is an optimization algorithm which is commonly-used to train machine learning models and neural networks. Training data helps these models learn over time, and the cost function within gradient descent specifically acts as a barometer, gauging its accuracy with each iteration of parameter updates. IBM Master Inventor Martin Keen explains.

#AI #Software #ITModernization #GradientDescent #lightboard #IBM #DataFabric #WatsonX

[Msyoutube]

Very nice explanation of the concept, brief and understandable. Awesome!

[davidrempel]

The most confusing part of this video is how he managed to write everything backwards on the glass so flawlessly

[krishnakeshav]

Good explanation. It is somewhat also important to note that curve should be differentiable.

[Shrimant-ubul]

Thank You Martin, really helpful for my uni exam

[harshsonar]

Im always confused by these screens or boards, whatever.
Like how do you write on them? Do you have to write backwards or do you write normally and it kinda mirrors it?

[sotirismoschos]

didn't know Steve Kerr works at IBM

[hugaexplit]

Very good explanation of high-level concept on GD.

[krissatish]

The best video i could find. Thank you.

[_alekss]

Nice I learned more from this 7 min video than 1 hour long boring lecture

[velo]

ibm: "how to make a neural network for the stock market?"

[Rajivrocks-Ltd.]

I was expecting a mathematical explanation :(

[abdulhamidabdullahimagama]

I couldn't visualise, I saw nothing on the screen...