You are on page 1of 112

Gradient Decent

Noman Naseer
• As you might have known by now that in Machine Learning, optimization
is used a lot.

• Gradient descent is an optimization algorithm.

• It is used to find a local minimum of a differentiable function.

• Gradient descent in ML is simply used to find the values of a function's


parameters (coefficients) that minimize a cost function as far as possible.
t-SNE (t-distributed Stochastic Neighbor Embedding) is an unsupervised non-linear dimensionality reduction technique for data
exploration and visualizing high-dimensional data.
49
Gradient Decent determines the step size by
multiplying the slope with a small number called the
learning rate.
When to Stop?
Putting Intercept = 0 and Slope = 1
Thank you

You might also like