Quiz di Neural Networks & Deep Learning

How neural networks really work: neurons and activations, losses, backpropagation, CNNs and the tricks that make deep networks train.

Intermedio 5 quiz · 50 domande circa 33 minuti
0/5superati Esame di categoria 20 domande miste. Con l'80% ottieni un certificato.
Tag:
1 Neurons & Activation Functions Facile Learn what a single neuron computes and how ReLU, sigmoid, tanh and softmax differ. #neural-networks#activations 10 domande · ~5 min Da iniziare Inizia
2 Forward Pass & Loss Functions Medio Follow data through a layer, count parameters and compute softmax and cross-entropy by hand. #neural-networks#loss 10 domande · ~6 min Da iniziare Inizia
3 Backpropagation & Gradient Descent Difficile Apply the chain rule, run gradient descent steps by hand and explain why training succeeds or fails. #backpropagation#gradient-descent#interview 10 domande · ~8 min Da iniziare Inizia
4 Convolutional Neural Networks (CNNs) Medio Calculate convolution output sizes and parameter counts and understand pooling and padding. #cnn#computer-vision 10 domande · ~6 min Da iniziare Inizia
5 Training Deep Networks Difficile Diagnose and fix real training problems with learning rates, dropout, batch norm and early stopping. #regularization#optimization 10 domande · ~8 min Da iniziare Inizia