Deep Learning
Deep learning is a subset of machine learning which provides the ability to
machine to perform human-like tasks without human involvement. It
provides the ability to an AI agent to mimic the human brain. Deep learning
can use both supervised and unsupervised learning to train an AI agent.
o Deep learning is implemented through neural networks architecture
hence also called a deep neural network.
o Deep learning is the primary technology behind self-driving cars,
speech recognition, image recognition, automatic machine translation,
etc.
o The main challenge for deep learning is that it requires lots of data
with lots of computational power.
How deep learning works:
o Deep Learning Algorithms work on deep neural networks, so it
is called deep learning. These deep neural networks are made
of multiple layers.
o The first layer is called an Input layer, the last layer is called
an output layer, and all layers between these two layers are
called hidden layers.
o In the deep neural network, there are multiple hidden layers,
and each layer is composed of neurons. These neurons are
connected in each layer.
o The input layer receives input data, and the neurons propagate
the input signal to its above layers.
o The hidden layers perform mathematical operations on inputs,
and the performed data forwarded to the output layer.
o The output layer returns the output to the user.
CNN
Deep Learning has proved to be a very powerful tool because of its
ability to handle large amounts of data. The interest to use hidden
layers has surpassed traditional techniques, especially in pattern
recognition. One of the most popular deep neural networks is
Convolutional Neural Networks (also known as CNN or ConvNet) in
deep learning, especially when it comes to Computer Vision
applications.
Convolutional Neural Networks a special type of neural network that
roughly imitates human vision.
What Is a CNN?
In deep learning, a convolutional neural
network (CNN/ConvNet) is a class of deep neural networks, most
commonly applied to analyze visual imagery. Now when we think of
a neural network we think about matrix multiplications but that is
not the case with ConvNet. It uses a special technique called
Convolution. Now in mathematics convolution is a mathematical
operation on two functions that produces a third function that
expresses how the shape of one is modified by the other.
[Link]
o Convolutional neural networks are composed of multiple layers of
artificial neurons. Artificial neurons, a rough imitation of their biological
counterparts, are mathematical functions that calculate the weighted
sum of multiple inputs and outputs an activation value. When you
input an image in a ConvNet, each layer generates several activation
functions that are passed on to the next layer.
o The first layer usually extracts basic features such as horizontal or
diagonal edges. This output is passed on to the next layer which
detects more complex features such as corners or combinational
edges. As we move deeper into the network it can identify even more
complex features such as objects, faces, etc.
Based on the activation map of the final convolution layer, the
classification layer outputs a set of confidence scores (values
between 0 and 1) that specify how likely the image is to belong to a
“class.” For instance, if you have a ConvNet that detects cats, dogs,
and horses, the output of the final layer is the possibility that the
input image contains any of those animals.
What Is a Pooling Layer?
Similar to the Convolutional Layer, the Pooling layer is responsible
for reducing the spatial size of the Convolved Feature. This is
to decrease the computational power required to process the
data by reducing the dimensions. There are two types of pooling
average pooling and max pooling.
CNN’s are used in many computer vision applications such as facial
recognition, image search, and editing, augmented reality.
What is Recurrent Neural Network (RNN)?
Recurrent Neural Network(RNN) is a type of Neural Network where the
output from the previous step is fed as input to the current step. In
traditional neural networks, all the inputs and outputs are
independent of each other. Still, in cases when it is required to predict
the next word of a sentence, the previous words are required and
hence there is a need to remember the previous words. Thus RNN
came into existence, which solved this issue with the help of a Hidden
Layer. The main and most important feature of RNN is its Hidden
state, which remembers some information about a sequence. The
state is also referred to as Memory State since it remembers the
previous input to the network. It uses the same parameters for each
input as it performs the same task on all the inputs or hidden layers
to produce the output. This reduces the complexity of parameters,
unlike other neural networks.
The fundamental processing unit in a Recurrent Neural Network (RNN)
is a Recurrent Unit, which is not explicitly called a “Recurrent
Neuron.” This unit has the unique ability to maintain a hidden state,
allowing the network to capture sequential dependencies by
remembering previous inputs while processing. Long Short-Term
Memory (LSTM) and Gated Recurrent Unit (GRU) versions improve the
RNN’s ability to handle long-term dependencies.
[Link] MODELING AND GENERATING TEXT
[Link] TRANSLATION
[Link] RECOGNITION
[Link] IMAGE DESCRIPTIONS
What is LSTM?
LSTM (Long Short-Term Memory) is a recurrent neural network
(RNN) architecture widely used in Deep Learning. It excels at
capturing long-term dependencies, making it ideal for sequence
prediction tasks.
Unlike traditional neural networks, LSTM incorporates feedback
connections, allowing it to process entire sequences of data, not just
individual data points. This makes it highly effective in
understanding and predicting patterns in sequential data like time
series, text, and speech.
LSTM models are widely used in artificial intelligence for natural
language processing tasks like language modeling and machine
translation. Some other applications of lstm are speech recognition,
image captioning, handwriting recognition, time series forecasting
by learning time series data, etc.