What is learnt in a neural network?1 pointWeights and BiasesOnly weightsOnly biasesNone of the above

In a neural network, what is learned are the Weights and Biases.

Here's a step-by-step explanation:

1. Initialization: When a neural network is first created, the weights and biases are usually initialized with random values.

2. Forward Propagation: The network takes in inputs and performs calculations using the current weights and biases to produce an output.

3. Backward Propagation: The output is compared to the expected output, and the error is calculated. This error is then propagated back through the network.

4. Adjustment: The weights and biases are adjusted in a way that would decrease the error if the same inputs were fed through the network again. This adjustment is done using a method called gradient descent.

5. Iteration: Steps 2-4 are repeated many times (often thousands or millions of times), each time adjusting the weights and biases to gradually improve the accuracy of the network's output.

6. Final Model: After many iterations, the weights and biases that the network has learned allow it to make accurate predictions or classifications when given new input data.

So, the answer to the question is "Weights and Biases".