A perceptron is: a) a single layer feed-forward neural network with pre-processing b) an auto-associative neural network c) a double layer auto-associative neural network d) a neural network that contains feedback

1 Answers  

---

Having multiple perceptrons can actually solve the XOR problem satisfactorily: this is because each perceptron can partition off a linear part of the space itself, and they can then combine their results. a) True – this works always, and these multiple perceptrons learn to classify even complex problems. b) False – perceptrons are mathematically incapable of solving linearly inseparable functions, no matter what you do c) True – perceptrons can do this but are unable to learn to do it – they have to be explicitly hand-coded d) False – just having a single perceptron is enough

1 Answers  

---

How are weights initialized in a network?

0 Answers  

---

How artificial neurons learns?

0 Answers  

---

How are artificial neural networks different from normal computers?

0 Answers  

---

Neural Networks are complex ______________ with many parameters. a) Linear Functions b) Nonlinear Functions c) Discrete Functions d) Exponential Functions

1 Answers  

---

What learning rate should be used for backprop?

0 Answers  

---

Describe the structure of artificial neural networks?

0 Answers  

---

What is a neural network and what are some advantages and disadvantages of such a network?

0 Answers  

---

What is backprop?

0 Answers  

---

Explain Generative Adversarial Network.

0 Answers  

---

Why use artificial neural networks? What are its advantages?

0 Answers  

---