I have learned about Multi-layer perceptron in which I understood forward propagation and backward propagation.

I learned about the Multi-layer Perceptrons and their key points: 1. Forward Propagation: Input --> Hidden --> Output 2. Back Propagation: Input <-- Hidden <-- Output (on going back it adjusts the weights of the input layer) 3. Learning rate: Controls how much the weights will be adjusted during backword propagation 4. Activation function: Used to introduce non-linear properties.

style of teaching is impresive

Multilayer perceptron (MLP) is an ANN that has hidden layers in it, that can handle complex and non linear functions. Its working i: Forward propagation: Signals move from input to output layer, and the activation functions are used by hidden and output layers. Backward propagation: Signals move from output to input layer. The errors are updated to the weights of neurons to improve accuracy. Learning rate: controls how much the weights are updated in back propagation. Activation functions: help to convert linear pattern to probability like Sigmoid, RELU, tanh

Done

The main discussion in this lecture is key points of multi-layer perceptron i,e forward propagation, backward propagation, learning rate and activation function

I learned in this lecture Multi-layer Perceptron (MLPs) 1-Input Layer ( receives the input signal, which is data ) 2-Hidden Layer ( one or more hidden layers ) 3-Output Layer ( produces the final output ) I also learned how it works so key points of working are 1-Key point no. one is Forward Propagation (signals travel from the input layer forward to the output) ( activation function used in the hidden and output layers only ) 2-Key point no. two is Back Propagation (updating the weights of neurons through the backpropagation method ) 3-Key point no. three is Learning Rate ( It controls how much the weights are adjusted during backpropagation )

I learned in this video Multi-layer Perceptron (MLPs) 1-Input Layer ( receives the input signal, which is data ) 2-Hidden Layer ( one or more hidden layers ) 3-Output Layer ( produces the final output ) I also learned how it works so key points of working are 1-Key point no. one is Forward Propagation (signals travel from the input layer forward to the output) ( activation function used in the hidden and output layers only ) 2-Key point no. two is Back Propagation (updating the weights of neurons through the back propagation method ) 3-Key point no. three is Learning Rate ( It controls how much the weights are adjusted during backpropagation )

AOA, I learned in this lecture about multi-layer perceptron (MLP), a type of neural network that consists of more than one layer of neurons. Unlike a single-layer perceptron, which can only learn linearly separable patterns, a multi-layer perceptron can learn more complex, non-linear functions. This makes it a fundamental model in the fields of deep learning and neural networks.And also learned structure of Multi-layer perceptrons, which are1-Input Layer ( receives the input signal, which is data ) 2-Hidden Layer ( one or more hidden layers ) 3-Output Layer ( produces the final output )And I also learned how it works so key points of working are1-Key point no. one is Forward Propagation (signals travel from the input layer forward to the output) ( activation function used in the hidden and output layers only )2-Key point no. two is Back Propagation (updating the weights of neurons through back propagation method )3-Key point no. three is Learning Rate ( It controls how much the weights are adjusted during back propagation )4-Key point no. four ( by mistake, three was written in the lecture) is Activation function ( functions like Sigmoid, ReLU or Tanh are allowing the MLP to learn more complex patterns.)ALLAH PAK aap ko sahat o aafiyat wali lambi umar ata kray aor ap ko dono jahan ki bhalian naseeb farmaey aur aap ke walid-e-mohtram ko karwat karwat jannat ata farmaye,Ameen.