<< Chapter < Page Chapter >> Page >
This module breaks down a standard neural network, describing the different parameters, hyper-parameters, and functions that are necessary for building a neural network.

Cost functions

The different cost functions we explored using were the sigmoid function, rectified linear units (ReLU), and the softmax normalization function.

Sigmoid function

Equation for the sigmoid activation function

The sigmoid activation function is the most general nonlinear activation function used in neural networks. Intuition would naively suggest that the activation of a neuron would be well modeled by the step function, but the issue is its non-differentiability. The stochastic gradient descent algorithm requires that activation functions be differentiable. The solution would be to approximate the step function using a smooth function like the sigmoid or the hyperbolic tangent. The issue with the sigmoid function is that its derivative far from the origin is near zero, so if any individual weight on a neuron is very wrong, it is unable to use the gradient to adjust its value. As a result, outlier weights can significantly impact the performance of the network.

Rectified linear units

Equation for the ReLU activation function

The advantage of using rectified linear units is threefold. First, its derivative is a constant (either 0 or 1) making the computation of the gradient much faster. Second, it is a better approximation of how biological neurons fire, in the sense that there is no activation in the absence of stimulation. Third, rectified linear units speed up learning by not being able to fire with zero net excitation. This means that if an excitation fails to overcome a neuron’s bias, the neuron will not fire at all. And when it does fire, the activation is linearly proportional to the excitation. The sigmoid function in comparison allows for some activation to occur with zero and even negative net excitation. However, a lower learning rate needs to be used with ReLU because its zero derivative for a net excitation less than zero means that the neuron effectively stops learning once its net excitation hits zero.


Equation for the softmax activation function

Softmax activation is particularly useful on the output layer, as it normalizes the output. Exponentiating each of the net excitations gives a more dramatic representation of the differences between them. Weak excitations become weaker activations and strong excitations become stronger activations. Everything is then normalized, giving the layer the effect of becoming a decision-maker.

Activation functions

The different cost functions we explored using for the gradient descent learning algorithm were mean-squared error, cross-entropy, and log-likelihood.

Mean-squared error

Equation for the mean-squared error cost function

Mean-squared error is the simplest measurement of difference that can be used to good effect in a neural network. It can be used with any activation function and is the more versatile option, though not always the most effective one. One of its shortcomings is that neurons with a sigmoid activation function become saturated quickly and are unable to learn more as a result of the relatively small magnitude of the sigmoid’s derivative far from the origin.


Equation for the cross-entropy cost function

Cross-entropy treats the desired output as some probability distribution and the network’s output as another probability distribution, and measures the distance between the distributions. The main attraction to using cross-entropy is that when used in conjunction with the sigmoid activation function, its gradient is linearly dependent on the error, solving the issue with neurons becoming saturated quickly.


Equation for the log-likelihood cost function

Log likelihood maximizes only the output neuron corresponding to which neuron should be firing. Used in conjunction with a softmax layer, all other output neurons would be minimized as a result of maximizing the desired output neuron. In this sense, a softmax layer has to be used, or the activations of the final layer will be too close together to draw meaningful conclusions.

Stochastic gradient descent

Stochastic gradient descent

Equation for the SGD learning algorithm, applied to both the weights and biases.

Stochastic gradient descent is the algorithm used in our network to adjust weights and biases according to the evaluation of the gradient of a given cost function. The gradient determines whether a parameter should increase or decrease and by how much. The learning rate of a network is a constant associated with how much a parameter should travel down its gradient at each reevaluation. In the original algorithm, parameters are updated after each given input. A common practice with neural nets is to only reevaluate the gradient after a so-called minibatch of multiple inputs is passed. This way, the cost function has multiple samples and can better construct a curve, yet the gradient is somewhat different every time it’s evaluated. This introduces some noise into the gradient to make it harder for parameters to get stuck in a local minimum of the gradient.


Overfitting is an issue experienced in networks when neurons are trained to identify specific images in a training set rather than the more general concept that an image represents. Instead of recognizing a 7, the network may only recognize the particular 7s that were in the training data set. To prevent this, we implemented dropout in our network. Random neurons in our interconnected layers were turned off between mini-batches, meaning that certain weights were not able to be used in determining an output. This essentially means that we were training a slightly different network each mini-batch, encouraging more neurons to learn meaningfully, as weights will typically be more fairly distributed. In evaluating the network, all neurons are turned back on and their weights are scaled down by the dropout rate. As a result, neurons are less strongly associated with particular images, and more applicable to a more expansive set of images.

Questions & Answers

Is there any normative that regulates the use of silver nanoparticles?
Damian Reply
what king of growth are you checking .?
What fields keep nano created devices from performing or assimulating ? Magnetic fields ? Are do they assimilate ?
Stoney Reply
why we need to study biomolecules, molecular biology in nanotechnology?
Adin Reply
yes I'm doing my masters in nanotechnology, we are being studying all these domains as well..
what school?
biomolecules are e building blocks of every organics and inorganic materials.
anyone know any internet site where one can find nanotechnology papers?
Damian Reply
sciencedirect big data base
Introduction about quantum dots in nanotechnology
Praveena Reply
what does nano mean?
Anassong Reply
nano basically means 10^(-9). nanometer is a unit to measure length.
do you think it's worthwhile in the long term to study the effects and possibilities of nanotechnology on viral treatment?
Damian Reply
absolutely yes
how to know photocatalytic properties of tio2 nanoparticles...what to do now
Akash Reply
it is a goid question and i want to know the answer as well
characteristics of micro business
for teaching engĺish at school how nano technology help us
Do somebody tell me a best nano engineering book for beginners?
s. Reply
there is no specific books for beginners but there is book called principle of nanotechnology
what is fullerene does it is used to make bukky balls
Devang Reply
are you nano engineer ?
fullerene is a bucky ball aka Carbon 60 molecule. It was name by the architect Fuller. He design the geodesic dome. it resembles a soccer ball.
what is the actual application of fullerenes nowadays?
That is a great question Damian. best way to answer that question is to Google it. there are hundreds of applications for buck minister fullerenes, from medical to aerospace. you can also find plenty of research papers that will give you great detail on the potential applications of fullerenes.
what is the Synthesis, properties,and applications of carbon nano chemistry
Abhijith Reply
Mostly, they use nano carbon for electronics and for materials to be strengthened.
is Bucky paper clear?
carbon nanotubes has various application in fuel cells membrane, current research on cancer drug,and in electronics MEMS and NEMS etc
so some one know about replacing silicon atom with phosphorous in semiconductors device?
s. Reply
Yeah, it is a pain to say the least. You basically have to heat the substarte up to around 1000 degrees celcius then pass phosphene gas over top of it, which is explosive and toxic by the way, under very low pressure.
Do you know which machine is used to that process?
how to fabricate graphene ink ?
for screen printed electrodes ?
What is lattice structure?
s. Reply
of graphene you mean?
or in general
in general
Graphene has a hexagonal structure
On having this app for quite a bit time, Haven't realised there's a chat room in it.
what is biological synthesis of nanoparticles
Sanket Reply
Got questions? Join the online conversation and get instant answers!
Jobilize.com Reply

Get the best Algebra and trigonometry course in your pocket!

Source:  OpenStax, Elec 301 projects fall 2015. OpenStax CNX. Jan 04, 2016 Download for free at https://legacy.cnx.org/content/col11950/1.1
Google Play and the Google Play logo are trademarks of Google Inc.

Notification Switch

Would you like to follow the 'Elec 301 projects fall 2015' conversation and receive update notifications?