Gradient Descent

In previous class we learn what is MLP? but we listen a term called gradient descent today we study gradient descent.

Gradient descent

In mathematics, gradient descent is a first-order iterative optimization algorithm for finding a local minimum of a differentiable function. The idea is to take repeated steps in the opposite direction of the gradient of the function at the current point, because this is the direction of steepest descent.

Here it is explained by image

Comments

How to train a neural network for Binary classification?

How to train a neural network for Binary classification ? 1. Install anaconda 2. Open jupyter notebook 3. Create file called app.py 4. Click Here to See Code

Perceptron

Perceptron is a general thing used in deep learning .You know what is neuron in brain Perceptron Layers 1. Input-In Input we provide Input to our model 2. Calculation-we calculate weight and biases for out Perceptron 3.Output-(sigma of wixi)+b Perceptron Architecture

What is Deep Learning?

Machine Learning Machine Learning is the subset of A.I it cannot extracts too hard features but its does not requires too much data Deep Learning Deep Learning is the subset of machine learning it can extracts difficult features but its requires too much data Which one I have to use? It is totally depends on data if you have too much data you can use deep learning else you can use machine learning

Deep Learning

Search This Blog