Deep Learning

Submitted to Submitted by
Dr. Lini Mathew

Md.MahfoozAlam(211516)
professor
Vishal Kumar (211517)
NITTTR Chandigarh
 Deep Learning:
Deep learning is the subset of machine learning which is based on artificial
neural network architecture.
 An artificial neural network uses layers of interconnected nodes called
neurons that work together to process and learn from the input data.
In a fully connected Deep neural network, there is an input layer and one
or more hidden layers connected one after the other.
 Each neuron receives input from the previous layer neurons or the input
layer.
 The output of one neuron becomes the input to other neurons in the next
layer of the network, and this process continues until the final layer
produces the output of the network.
 The layers of the neural network transform the input data through a series
of nonlinear transformations, allowing the network to learn complex
representations of the input data.
Example of Deep Learning:
Artificial neural networks:

Artificial neural network is a machine learning approach

that models human brain and consists of a number of
artificial neurons.
Neuron in ANNs tend to have fewer connections than
biological neurons.
Each neurons in ANN receives a number of inputs.

An activation function is applied to these inputs which results in

activation level of neuron .

Knowledge about the learning task is given in the form of examples

called training examples.

An artificial neural network is simplified by:

• Neuron model : The information processing unit of the NN.
• An architecture : A set of neurons and links connecting
neurons .Each link has a weight.
• A learning algorithm: Used for training the NN by modifying the
weights in order to model a particular learning task correctly on
the training examples.
The aim is to obtain a NN that is trained and generalizes
well.
It should behaves correctly on new instances of the learning
task.
Machine Learning vs Deep Learning:
Machine Learning and Deep Learning are the two main
concepts of Data Science and the subsets of Artificial
Intelligence.
Most of the people think the machine learning, deep
learning, and as well as artificial intelligence as the same
buzzwords. But in actuality, all these terms are different but
related to each other.
Working of Machine Learning:
The ML model takes images of both cat and dog as input.
Extracts the different features of images such as shape,
height, nose, eyes, etc.
Applies the classification algorithm, and predict the output.
 Working of Deep learning:
 The deep learning model takes the images as the input and
feed it directly to the algorithms without requiring any manual
feature extraction step.
 The images pass to the different layers of the artificial neural
network and predict the final output.
Difference between machine learning and Deep
learning:
Machine Learning Deep Learning
1. Apply statistical algorithms to learn 1.Uses artificial neural network
the hidden patterns and relationships in architecture to learn the hidden pattern
the dataset. and relationships in the dataset.
2. Can work on the smaller amount of 2. Requires the larger volume of dataset
Dataset. compared to machine learning.
3. Better for the low-label task. 3. Better for complex task like image
processing, natural language processing,
etc.
4. Takes less time to train the model. 4. Takes more time to train the model.
5. Less complex and easy to interpret 5. More complex, it works like the black
the result. box interpretations of the result are not
easy.
6. It can work on the CPU or requires 6. It requires a high-performance
less computing power as compared to computer with GPU.
deep learning.
Types of neural networks:
Feedforward neural networks (FNNs): are the simplest type of ANN,
with a linear flow of information through the network. FNNs have
been widely used for tasks such as image classification, speech
recognition, and natural language processing.
 Convolutional Neural Networks (CNNs): are specifically for image
and video recognition tasks. CNNs are able to automatically learn
features from the images, which makes them well-suited for
tasks such as image classification, object detection, and image
segmentation.
Recurrent Neural Networks (RNNs): are a type of neural network
that is able to process sequential data, such as time series and
natural language. RNNs are able to maintain an internal state
that captures information about the previous inputs, which
makes them well-suited for tasks such as speech recognition,
natural language processing, and language translation.
 Applications of Deep Learning :
Computer vision:
• Object detection and recognition: Deep learning model can
be used to identify and locate.
• Image classification: Deep learning models can be used to
classify images into categories such as animals, plants, and
buildings. This is used in applications such as medical
imaging, quality control, and image retrieval.
• Image segmentation: Deep learning models can be used for
image segmentation into different regions, making it
possible to identify specific features within images.
Natural language processing (NLP):

• Automatic Text Generation : Deep learning model can learn the

corpus of text and new text like summaries, essays can be
automatically generated using these trained models.
• Language translation: Deep learning models can translate text from one
language to another, making it possible to communicate with people from
different linguistic backgrounds.
• Sentiment analysis: Deep learning models can analyze the
sentiment of a piece of text, making it possible to determine
whether the text is positive, negative, or neutral. This is used in
applications such as customer service, social media monitoring,
and political analysis.
• Speech recognition: Deep learning models can recognize and
transcribe spoken words, making it possible to perform tasks
such as speech-to-text conversion, voice search, and
voicecontrolled devices
Reinforcement learning:

• Game playing: Deep reinforcement learning models have been able

to beat human experts at games such as Go, Chess, and Atari.
• Robotics: Deep reinforcement learning models can be used to train
robots to perform complex tasks such as grasping objects,
navigation, and manipulation.
• Control systems: Deep reinforcement learning models can be used
to control complex systems such as power grids, traffic
management, and supply chain optimization.
Advantages of Deep Learning:
High accuracy: Deep Learning algorithms can achieve state-of-the-art
performance in various tasks, such as image recognition and natural
language processing.
 Automated feature engineering: Deep Learning algorithms can
automatically discover and learn relevant features from data without
the need for manual feature engineering.
 Scalability: Deep Learning models can scale to handle large and
complex datasets, and can learn from massive amounts of data.
 Flexibility: Deep Learning models can be applied to a wide range of
tasks and can handle various types of data, such as images, text, and
speech.
 Continual improvement: Deep Learning models can continually
improve their performance as more data becomes available.
Disadvantages of Deep Learning:
High computational requirements: Deep Learning models
require large amounts of data and computational resources to
train and optimize.
Requires large amounts of labeled data: Deep Learning models
often require a large amount of labeled data for training, which
can be expensive and time- consuming to acquire.
Interpretability: Deep Learning models can be challenging to
interpret, making it difficult to understand how they make
decisions.
Overfitting: Deep Learning models can sometimes overfit to
the training data, resulting in poor performance on new and
unseen data.
Black-box nature: Deep Learning models are often treated as
black boxes, making it difficult to understand how they work
and how they arrived at their predictions.