Deep Learning concepts

LIMITATIONS OF MACHINE LEARNING

• Are not useful while working with high dimensional data, that is where we have large
number of inputs and outputs.
• Cannot solve crucial AI problems like NLP, Image Recognition, etc.
• One of the biggest challenge with traditional Machine Learning Models is a process called
Feature Extraction. For complex problems such as object recognition or handwriting
recognition
 Introduction to Deep learning

• Deep learning can be considered as a subset of machine learning. It is

a field that is based on learning and improving on its own by
examining computer algorithms. While machine learning uses simpler
concepts, deep learning works with artificial neural networks, which
are designed to imitate how humans think and learn.
• Deep learning is implemented with the help of Neural Networks, and
the idea behind the motivation of Neural Network is the biological
neurons, which is nothing but a brain cell.
Artificial neural networks, comprising many layers, drive deep learning. Deep Neural Networks (DNNs) are
such types of networks where each layer can perform complex operations such as representation and
abstraction that make sense of images, sound, and text.
 DEEP LEARNING APPLICATIONS

• Natural Language Processing:It is the procedure for allowing robots to study and comprehend human
language.
• Virtual Assistants:Virtual Assistants are cloud-based applications that understand natural language voice
commands and complete tasks for the user.
• Chatbots:A chatbot is an AI application to chat online via text or text-to-speech. It is capable of communicating
and performing actions similar to a human. Chatbots are used a lot in customer interaction, marketing on social
network sites, and instant messaging the client.
• Image Coloring:Image colorization has seen significant advancements using Deep Learning. Image colorization
is taking an input of a grayscale image and then producing an output of a colorized image. ChromaGAN is an
example of a picture colorization model.
• Image Captioning:Image Captioning is the method of generating a textual description of an image. It uses
computer vision to understand the image's content and a language model to turn the understanding of the
image into words in the right order.
• Self Driving Cars:Deep Learning is the driving force behind the notion of self-driving automobiles that are
autonomous. Deep Learning technologies are actually "learning machines" that learn how to act and respond
using millions of data sets and training.
• Visual Recognition:Visual recognition is perceiving an item, animal, or person and knowing what is because you
have seen it before or seen something similar. When we recognize something, we compare something in view
to the huge library in our visual memory.
 How Deep Learning Work?
Neural networks are layers of nodes, much like the human brain is made up of neurons. Nodes within individual layers are
connected to adjacent layers. The network is said to be deeper based on the number of layers it has. A single neuron in the
human brain receives thousands of signals from other neurons. In an artificial neural network, signals travel between nodes
and assign corresponding weights. A heavier weighted node will exert more effect on the next layer of nodes. The final layer
compiles the weighted inputs to produce an output.
Working of neural networks
 TYPES OF NEURAL NETWORK
FEED FORWRAD NEURAL NETWORK

Feed-forward neural networks allows signals to travel one

approach only, from input to output. There is no feedback
(loops) such as the output of some layer does not influence
that same layer. Feed-forward networks tends to be simple
networks that associates inputs with outputs. It can be used in
pattern recognition. This type of organization is represented as
bottom-up or top-down. In this kind of neural network, all the
perceptrons are organized within layers, such that the input
layer takes the input, and the output layer generates the Applications:
output. Since the hidden layers do not link with the outside •Data Compression
world, it is named as hidden layers. Each of the perceptrons •Pattern Recognition
contained in one single layer is associated with each node in •Computer Vision
the subsequent layer. It can be concluded that all of the nodes •Sonar Target Recognition
are fully connected. It does not contain any visible or invisible •Speech Recognition
connection between the nodes in the same layer. •Handwritten Characters Recognition
 TYPES OF NEURAL NETWORK
Recurrent Neural Network
Here each of the neurons present in the hidden layers
receives an input with a specific delay in time. The
Recurrent neural network mainly accesses the
preceding info of existing iterations. For example, to
guess the succeeding word in any sentence, one must
have knowledge about the words that were previously
used. It not only processes the inputs but also shares the
length as well as weights crossways time. It does not let
the size of the model to increase with the increase in the Applications:
•Machine Translation
input size
•Robot Control
•Time Series Prediction
•Speech Recognition
•Speech Synthesis
•Time Series Anomaly Detection
•Rhythm Learning
•Music Composition
 TYPES OF NEURAL NETWORK
Convolutional Neural Network

Convolutional Neural Network 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.

Applications:
•Identify Faces, Street Signs, Tumors.
•Image Recognition.
•Video Analysis.
•NLP.
•Anomaly Detection.
•Drug Discovery.
•Checkers Game.
•Time Series Forecasting.
 TYPES OF NEURAL NETWORK
S.no CNN RNN
1 CNN stands for Convolutional Neural RNN stands for Recurrent Neural Network.
Network.

2 CNN is considered to be more potent than RNN. RNN includes less feature compatibility when compared to
CNN.
3 CNN is ideal for images and video processing. RNN is ideal for text and speech Analysis.

4 It is suitable for spatial data like images. RNN is used for temporal data, also called sequential data.

5 The network takes fixed-size inputs and RNN can handle arbitrary input/ output lengths.
generates fixed size outputs.

6 CNN is a type of feed-forward artificial neural RNN, unlike feed-forward neural networks- can use their
network with variations of multilayer internal memory to process arbitrary sequences of inputs.
perceptron's designed to use minimal amounts of
preprocessing.

7 CNN's use of connectivity patterns between the Recurrent neural networks use time-series information- what a
neurons. CNN is affected by the organization of user spoke last would impact what he will speak next.
the animal visual cortex, whose individual
neurons are arranged in such a way that they can
respond to overlapping regions in the visual
field.
 TYPES OF NEURAL NETWORK

Criteria Artificial Neural Networks (ANNs) Convolutional Neural Networks (CNNs)

Architecture Multilayer perceptron Convolutional layers, pooling layers, and fully
connected layers
Feature extraction Hand-crafted or learned features Learned features through convolutional layers
Spatial information Not specifically designed to capture spatial structure Specifically designed to capture the spatial
structure of images
Parameter sharing No parameter sharing Parameter sharing through convolutional layers
Scalability Less scalable due to the high number of parameters and overfitting More scalable due to shared weights and
hierarchical representations
Training data Requires a large amount of training data to avoid overfitting More efficient use of training data due to
parameter sharing
Transfer learning Less effective for transfer learning Effective for transfer learning due to pre-trained
models on large datasets
Computational efficiency Less computationally efficient, especially for large images or deep More computationally efficient, especially for
architectures large images or deep architectures

Accuracy Can achieve high accuracy on image classification tasks Can achieve higher accuracy than ANNs on
image classification tasks
S. No. Machine Learning Deep Learning

1. Machine Learning is a superset of Deep Learning Deep Learning is a subset of Machine Learning

The data represented in Machine Learning is quite

The data representation used in Deep Learning is quite different as it uses
2. different compared to Deep Learning as it uses
neural networks(ANN).
structured data

Deep Learning is an evolution of Machine Learning. Basically, it is how deep is

3. Machine Learning is an evolution of AI.
the machine learning.

4. Machine learning consists of thousands of data points. Big Data: Millions of data points.

Outputs: Numerical Value, like classification of the Anything from numerical values to free-form elements, such as free text and
5.
score. sound.

Uses various types of automated algorithms that turn

Uses a neural network that passes data through processing layers to,
6. to model functions and predict future action from
interpret data features and relations.
data.

Algorithms are detected by data analysts to examine Algorithms are largely self-depicted on data analysis once they’re put into
7.
specific variables in data sets. production.

Machine Learning is highly used to stay in the

8. Deep Learning solves complex machine-learning issues.
competition and learn new things.

Training can be performed using the CPU (Central

9. A dedicated GPU (Graphics Processing Unit) is required for training.
Processing Unit).
Although more difficult to set up, deep learning requires less intervention
10. More human intervention is involved in getting results.
once it is running.