Scribd Logo
Upload

Welcome to Scribd!

  • 100 views

    ML Quiz 2

    Uploaded by

    Ruwayda Ibraheem
    This document summarizes key concepts about neural networks, recurrent neural networks, and long short-term memory networks. It addresses topics like the numeric input requirement for neural networks, the purpose of nonlinear activation functions, appropriate activation functions at different layers and for different models, the role of gradient in finding optimal weights, dropout as a regularization technique, and the different gates in an LSTM and their purposes.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    ML Quiz 2

    Uploaded by

    Ruwayda Ibraheem
    100 views1 page
    This document summarizes key concepts about neural networks, recurrent neural networks, and long short-term memory networks. It addresses topics like the numeric input requirement for neural networks, the purpose of nonlinear activation functions, appropriate activation functions at different layers and for different models, the role of gradient in finding optimal weights, dropout as a regularization technique, and the different gates in an LSTM and their purposes.

    Original Title

    ML quiz 2

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document summarizes key concepts about neural networks, recurrent neural networks, and long short-term memory networks. It addresses topics like the numeric input requirement for neural networks, the purpose of nonlinear activation functions, appropriate activation functions at different layers and for different models, the role of gradient in finding optimal weights, dropout as a regularization technique, and the different gates in an LSTM and their purposes.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    100 views1 page

    ML Quiz 2

    Uploaded by

    Ruwayda Ibraheem
    This document summarizes key concepts about neural networks, recurrent neural networks, and long short-term memory networks. It addresses topics like the numeric input requirement for neural networks, the purpose of nonlinear activation functions, appropriate activation functions at different layers and for different models, the role of gradient in finding optimal weights, dropout as a regularization technique, and the different gates in an LSTM and their purposes.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 1

    ML quiz 2 (NN, RNN)

    1. Neural networks accept only numeric values as input?


    True

    2. In neural networks nonlinear activation function such as sigmoid, relu


    help in:
    Help learn nonlinear decision boundary

    3. Use activation function in hidden layer NN as … the output is -0.0001


    what is the activation function:
    Tanh

    4. Gradient is equal to zero means we find the minimal weight


    True

    5. Dropout is a regularization technique where we randomly set some


    activation function to zero during:
    Training

    6. When building simple RNN we used sigmoid and tanh as activation


    function:
    True

    7. Deep RNN we used:


    Relu

    8. In LSTM the gate that is responsible of deciding what is the next hidden
    state is:
    Output gate

    9. In LSTM the gate that is responsible of deciding Which information


    should kept or thrown is:
    Forget gate

    10. If the network has only the input layer and the output layer and used
    sigmoid function as activation the neural networks is basically:
    Logistic regression

    >3 ‫بالتوفيق‬
    ‫ال تنسوني من دعائكم‬

    You might also like