Let’s take a quick look at what you have learnt in this session.

Some important points can be summarised as follows:

- Firstly, you understood the limitations of preliminary machine learning and how deep learning can be used to build complex models.
- Next, you saw how the architecture of ANNs draws inspiration from the human brain.
- You also learnt about the basic functioning of a perceptron.
- Further, you learnt about the basic building block of ANNs: Neurons. The structure of an artificial neuron is shown below.

Here, ‘a’ represents the inputs, ‘w’ represents the weights associated with the inputs, and ‘b’ represents the bias of the neuron.

- You then learnt about the architecture of ANNs, including the topology, the parameters (weights and biases) on which the neural network is trained and the hyperparameters.
- ANNs only take numerical inputs. Hence, you need to convert all types of data into a numeric format so that neural networks can process it.
- Next, you were introduced to the most common activation functions such as sigmoid, ReLU, Leaky ReLU and tanh, which are shown below.
- Some simplifying assumptions in the architecture of ANNs are as follows.

- The neurons in an ANN are
**arranged in layers**, and these layers are arranged**sequentially**. - The neurons within the same layer
**do not interact**with each other. - The inputs are fed into the network through the
**input layer**, and the outputs are sent out from the**output layer**. - Neurons in
**consecutive layers**are**densely connected**, i.e., all neurons in layer l are connected to all neurons in layer l+1. - Every neuron in the neural network has a
**bias**value associated with it, and each interconnection has a**weight**associated with it. - All neurons in a particular hidden layer use the
**same activation function**.

9. Finally, you fixed the following notations:

- W represents the weight matrix.
- b stands for bias.
- x represents input.
- y represents the ground truth label.
- p represents the probability vector of the predicted output for the classification problem.
- h represents the output of the hidden layers, and hL represents the output prediction for the regression problem.
- z represents the cumulative input fed into each neuron of a layer.
- The superscript represents the layer number.
- The subscript represents the index of each individual neuron in a layer.

In the next segment, you will attempt some graded questions to test your understanding of the topics covered in this session. All the best!

Report an error