← Back to Neural networks
All 10 questions. After you submit, each question shows the right answer and why. Back to the quick check
An artificial neural network is an exact computer copy of a human brain.
In an artificial neural network, the connections between units can be made stronger or weaker, a bit like the synapses between brain cells.
The ReLU activation function, max(0, z), turns a negative number into what?
Which logic function cannot be computed by a single linear unit but can be computed by a network with one hidden layer of two units?
A neuron has weights 20 and 20 and bias −30. Both inputs are 1. What is its weighted sum z (before the activation function)?
What did Rumelhart, Hinton and Williams (1986) say back-propagation repeatedly adjusts?
Who received the 2024 Nobel Prize in Physics for foundational work enabling machine learning with artificial neural networks?
What did the 1986 back-propagation paper highlight as the key advantage over the earlier perceptron-convergence procedure?
The universal approximation theorem guarantees that gradient-based training will find weights that approximate any target function.
In one or two sentences, define deep learning as LeCun, Bengio and Hinton did in Nature (2015), naming the algorithm that drives it.
