NEURAL NETWORKS

A Guide to Computational and Deep Learning

 INTRODUCTION
Neural networks are a set of algorithms, modeled
loosely after the human brain
They are designed to recognize patterns by interpreting
data through machine perception, and then labeling or
clustering the raw input.
 They recognize patterns by converting raw input to
numerical, vectorized data, into which all real-world
data, such as images, sound, text or time series, can be
translated.
 HOW DO THEY MIMIC THE
BRAIN?
A neural network is either a biological neural network, made up of real
biological neurons, or an artificial neural network, designed to recognize
patterns and solve problems.

Artificial neural networks try to mimic the biological neural network in the
human brain.

A typical brain contains close to 100 billion miniscule cells called neurons.
Each neuron is made up of a cell body with a number of connections
coming off it: numerous dendrites (the cell’s inputs—carrying information
toward the cell body) and a single axon (the cell’s output—carrying
information away).

Dendrites extend from the neuron cell body and receive messages from
other neurons. When neurons receive or send messages, they transmit
electrical impulses along their axons that aid in carrying out functions such
as storing memories, controlling muscles, and more.
 HOW DO THEY MIMIC THE
BRAIN?There are areas, however, where the simplified
model of the artificial neural network does not
quite mimic the brain exactly.
For example, it can’t mimic the creation or
destruction of connections (dendrites or axons)
between neurons, and it ignores signal timing.

 Still, artificial neural networks are quite effective considering how they’re used in various applications, and
have become smarter over time.

 Many modern applications rely on them including: driverless cars, object classification and detection,
personalized recommendations, language translation, speech recognition, image tagging, and much more.
 HOW DO NEURAL
NETWORKS WORK?
Similar to the human brain, an artificial neural network is made of artificial neurons that work together to solve a
problem.
Artificial neurons are software modules, called nodes, and artificial neural networks are software programs or
algorithms that, at their core, use computing systems to solve mathematical calculations.
A basic neural network has interconnected artificial neurons in three layers:
Input Layer: Information from the outside world enters the artificial neural network from the
input layer. Input nodes process the data, analyze or categorize it, and pass it on to the next layer.

Hidden Layer: Hidden layers take their input from the input layer or other hidden layers.
Artificial neural networks can have a large number of hidden layers. Each hidden layer analyzes
the output from the previous layer, processes it further, and passes it on to the next layer.

Output Layer: The output layer gives the final result of all the data processing by the artificial
neural network. It can have single or multiple nodes. For instance, if we have a binary (yes/no)
classification problem, the output layer will have one output node, which will give the result as 1
or 0. However, if we have a multi-class classification problem, the output layer might consist of
more than one output node.
 DEEP NEURAL NETWORK
ARCHITECTURE Deep neural networks, or deep learning
networks, have several hidden layers with
millions of artificial neurons linked
together.
A number, called weight, represents the
connections between one node and
another. The weight is a positive number if
one node excites another, or negative if
one node suppresses the other.
Nodes with higher weight values have
more influence on the other nodes.

• Theoretically, deep neural networks can map any input type to any output type.
• However, they also need much more training as compared to other machine learning methods.
They need millions of examples of training data rather than perhaps the hundreds or
thousands that a simpler network might need.
 DEEP NEURAL NETWORK
ARCHITECTUREArtificial intelligence is the field of
computer science that researches
methods of giving machines the
ability to perform tasks that require
human intelligence.
Machine learning is an artificial
intelligence technique that gives
computers access to very large
datasets and teaches them to learn
from this data.
• Machine learning software finds patterns in existing data and applies those patterns to new
data to make intelligent decisions.
• Deep learning is a subset of machine learning that uses deep learning networks to process
data.
 MACHINE LEARNING VS.
DEEP LEARNING
Conventional machine learning techniques require human input for the machine learning software to work
sufficiently well. A data scientist manually determines the set of relevant features that the software must
analyze. This limits the software’s ability, which makes it tedious to create and manage.
In deep learning, the data scientist feeds only raw data to the software. The deep learning network derives the
features by itself and learns more independently. It can analyze unstructured datasets like text documents,
identify which data attributes to prioritize, and solve more complex problems.

For example, if you were training a machine learning software to identify an image of a pet correctly, you
would need to take these steps:

1. Find and label thousands of pet images, like cats, dogs, horses, hamsters, parrots, and so on, manually.
2. Tell the machine learning software what features to look for so it can identify the image using elimination. For instance, it
might count the number of legs, then check for eye shape, ear shape, tail, fur, and so on.
3. Manually assess and change the labeled datasets to improve the software’s accuracy. For example, if your training set has too
many pictures of black cats, the software will correctly identify a black cat but not a white one.

In deep learning, however, the neural networks would process all the images and automatically determine that
they need to analyze the number of legs and the face shape first, then look at the tails last to correctly identify
 TYPES OF NEURAL
NETWORKS
Neural networks can be categorized by how the data flows
from the input node to the output node.
Artificial Neural Network (ANN): is a Feed-Forward
Neural network because inputs are processed only in the
forward direction from the input node to the output node.
Every node in one layer is connected to every node in the
next layer.
Essentially, each layer tries to learn certain weights.
A feed-forward network uses a feedback process to
improve predictions over time.
ANN can be used to solve problems related to: Tabular
data, Image data, and Text data
TYPES OF NEURAL
NETWORKS
Recurrent Neural Network (RNN): is
similar to an ANN but has a recurrent
connection on the hidden state.
This looping constraint ensures that
sequential information is captured in the
input data.
We can use recurrent neural networks to
solve the problems related to: Time Series
data, Text data and Audio data
 TYPES OF NEURAL
NETWORKS

Convolutional Neural Network (CNN): The hidden layers in in CNNs perform specific mathematical
functions, like summarizing or filtering, called convolutions.
The building blocks of CNNs are filters or kernels. Kernels are used to extract the relevant features from
the input using the convolution operation.
They are very useful for image classification because they can extract relevant features from images that
are useful for image recognition and classification.
The new form is easier to process without losing features that are critical for making a good prediction.
Each hidden layer extracts and processes different image features, like edges, color, and depth.
 ADVANTAGES OF NEURAL
NETWORKS
Neutral networks that can work continuously and are more efficient than humans or simpler
analytical models. Neural networks can also be programmed to learn from prior outputs to
determine future outcomes based on the similarity to prior inputs.

Neural networks that leverage cloud of online services also have the benefit of risk
mitigation compared to systems that rely on local technology hardware. In addition, neural
networks can often perform multiple tasks simultaneously (or at least distribute tasks to be
performed by modular networks at the same time).

Last, neural networks are continually being expanded into new applications. While early,
theoretical neural networks were very limited to its applicability into different fields, neural
networks today are leveraged in medicine, science, finance, agriculture, or security.
DISADVANTAGES OF NEURAL
NETWORKS
Though neutral networks may rely on online platforms, there is still a hardware component that is
required to create the neural network. This creates a physical risk of the network that relies on
complex systems, set-up requirements, and potential physical maintenance.

Though the complexity of neural networks is a strength, this may mean it takes months (if not longer)
to develop a specific algorithm for a specific task. In addition, it may be difficult to spot any errors or
deficiencies in the process, especially if the results are estimates or theoretical ranges.

Neural networks may also be difficult to audit. Some neural network processes may feel "like a black
box" where input is entered, networks perform complicated processes, and output is reported. It may
also be difficult for individuals to analyze weaknesses within the calculation or learning process of
the network if the network lacks general transparency on how a model learns upon prior activity.