alleryStart learning →M.Tech AI/ML Postgraduate Computing — practice questions
Explore 21 free Postgraduate Computing questions in M.Tech AI/ML Computer Science. Each question opens with answer choices, the correct answer and a worked solution.
Practise Postgraduate Computing with Quill →Postgraduate Computing MCQs with answers
Showing questions 1–21 of 21.
A structure built from small decision making units is a neural:Read the answer and worked solution →The main purpose of a neural network is to do what with complex data?Read the answer and worked solution →A famous training dataset of handwritten digits is used for image processing and:Read the answer and worked solution →The way neurons work in a network is said to be analogous to neurons in the:Read the answer and worked solution →Data first enters a neural network at the:Read the answer and worked solution →A neuron sends a signal only when it receives the right input. That sending is called:Read the answer and worked solution →After the last hidden layer, the signal passes to the:Read the answer and worked solution →With several output neurons, the network's answer is the one with highest:Read the answer and worked solution →Each connection between two neurons carries how many parameters?Read the answer and worked solution →The value multiplied by an incoming signal is called the:Read the answer and worked solution →The value added to a weighted signal, making activation more or less likely, is the:Read the answer and worked solution →In a network with four layers, how many of them are hidden?Read the answer and worked solution →A network with multiple hidden layers, developed in the 1980s, is the multilayer:Read the answer and worked solution →A model that fits its training data too closely and generalises poorly shows:Read the answer and worked solution →The function used to measure error in a neural network is the:Read the answer and worked solution →Training adjusts weights and biases in a way that reduces the:Read the answer and worked solution →Learning in a neural network is essentially minimising the loss over all:Read the answer and worked solution →Training steps are repeated until the model reaches a sufficient level of:Read the answer and worked solution →A loss function used when the goal is to predict continuous values suits:Read the answer and worked solution →A loss function used when the output is either 0 or 1 suits binary:Read the answer and worked solution →The closer average loss is to zero, the smaller the:Read the answer and worked solution →
How to practise
- Choose a Postgraduate Computing question and try to work out your answer.
- Open the question to check the correct answer and read its worked solution.
- Continue in the app for bite-sized lessons, explanations and review with Quill. You can start without creating an account.