Week Five - Pre-Assessment
The neural network training is done by defining a performance function.
True
The development process for an ANN application involves <blank> steps.
nine
A neuron is a processing unit that performs a set of predefined mathematical operations on numerical values coming from the input variables or from the other neurons outputs to create and push out its outputs.
true
An RNN models a dynamic system.
true
The <blank> is caused by extremely small derivatives of sigmoid functions in some regions of the images.
vanishing gradient problem
The <blank> enables software developers to use GPUs made by NVIDIA for general-purpose processing.
Compute Unified Device Architecture (CUDA)
the initial idea for deep learning began in 2013.
False
<blank> uses deep learning artificial neural network algorithms to deliver information about the images captured by users from their nearby objects.
Google Lens
The growth in the use of deep neural networks has been spurred by advancements in GPU hardware technology.
True
<Blank> is the most widely used supervised learning algorithm in neural computing.
back propagation
A CNN is restricted to image datasets.
false
Deep neural networks are referred to as "deep" because they are primarily used to evaluate significant philosophical issues.
false
In artificial neurons, weight terms are adjustable but biased terms are fixed.
false
The task undertaken by a neural network does not affect the architecture of the neural network; in other words, architectures are problem-independent.
false
Theano is a C++ library developed by the Deep Learning Group at the University of Montreal.
false
<blank> is an open-source neural network library that functions as a high-level API.
keras
<blank> refers to a subfield of AI that employs computer programs to change speech or text from one language to another.
machine translation
The <blank> learning is a type of machine learning that focuses on learning and discoving features by the system in addition to discovering the mapping from those features to the output.
representation
The pooling layer, also known as the <blank> layer, follows the convolution layer.
subsampling
A <blank> is used to compute the weighted sums of all input elements entering each processing element.
summation function
