วีดีโอ

GPU means graphics processing unit (GPU) ,is a hardware component that you can add to your device. GPU can perform mathematical calculations at high speed. Computing tasks like graphics rendering, machine learning (ML), and video editing require the application of similar mathematical operations on a large dataset.

Initial weights for Networks and bias will be given in the question ... If the weights are not given then initially we can assign random values and update it at each training iterations during network training process.

Hi, If your query is on how to get back the output in Table?Then you can try writing the output to excel.

Thank you.. There are many good Books for Neural Networks.. To highlight, 1.Fundamentals of Neural Networks: Architectures, Algorithms and Applications, Laurene V. Fausett 2.Neural Networks and learning machines, Simon Haykin

@@Dr.NancyJane thanks mam.

Thank you sir.

In Mcculloch Pitts neuron model we have to fix the threshold for activation. That is it's limitation.. For AND Gate when two inputs are 1 the output is 1 so to map this we set the threshold to be any constant greater than the input weights. You can keep any constant threshold value but see to it that the activated output it generates should be 1 only when two inputs are high. Here for simplicity we kept threshold for activation as 2 and weights as 1.

In Mcculloch Pitts neuron model we have to fix the threshold for activation. That is it's limitation.. For AND Gate when two inputs are 1 the output is 1 so to map this we set the threshold to be any constant greater than the input weights. You can keep any constant threshold value but see to it that the activated output it generates should be 1 only when two inputs are high. Here for simplicity we kept threshold for activation as 2 and weights as 1.

Yes.

Yes. Only the initial weights

Initial weights are randomly selected

Accuracy measures the proportion of correct predictions out of total predictions made. It's calculated as: Accuracy = (TP + TN) / (TP + TN + FP + FN) Precision measures the proportion of true positives among all positive predictions made. It's calculated as: Precision = TP / (TP + FP)

th-cam.com/video/pnSwBUL2sP4/w-d-xo.htmlsi=jBzSE5KS2YvZkKOC

These are only basics.. You have many more topics to explore...