Explain Deep learning ?

Deep learning is a part of machine learning which is a subset of AI,

that’s tries to mimic the way of our brain use to solve the complex
problems. It’s like teaching computer to solve, learn and make
decision by it self just like humans do.

Deep learning uses ANN to reach accurate conclusions without

human intervention.

Deep learning algorithms are specially used when we have huge

number of input outputs.
Write down five deep learning algorithms ?

CNN (convolutional neural network)

Known as ConvNets , majorly consist of several layers and are specifically use for image processing and
detection of objects.

CNNs process the data by passing it through the multiple layers and extract the features.

Convolutional layer consist of ReLU (Rectified Linear Unit) that outlast to rectify the feature map.

Pooling layer : is used to rectify these feature maps into next feed.

Fully connected layer : which forms the flattened matrix or 2D array fetched from the pooling layer as input
and identifies the image by classifying it.

Long Short Term Memory Networks (LSTMs)

LSTMs can be defined as Recurrent Neural Networks (RNN) that are programmed to learn and adapt for dependencies
for the long term.
It can memorize and recall past data for a greater period and by default, it is its sole behavior.
LSTMs are designed to retain over time and henceforth they are majorly used in time series predictions because they can
restrain memory or previous inputs.
they can be used to construct speech recognizers, development in pharmaceuticals, and composition of music loops as
well.
RNNs RNNs is that they store historical information and there's no increase in the input size even if the model size
is increased. RNNs look something like this when unfolded.

Generative Adversarial Networks (GANs)

GANs are defined as deep learning algorithms that are used to generate new
instances of data that match the training data.
GAN usually consists of two components namely a
generator that learns to generate false data and a
discriminator that adapts itself by learning from this false data.

It is also used in video games to increase graphics for 2D textures by recreating

them in higher resolution like 4K. They are also used in creating realistic cartoons
character and also rendering human faces and 3D object rendering.
Radial Basis Function Networks (RBFNs)
RBFNs are specific types of neural networks that follow a feed-forward
approach and
make use of radial functions as activation functions.

They consist of three layers namely the input layer, hidden

layer, and output layer which are mostly used for time-series
prediction, regression testing, and classification.

Multilayer Perceptrons (MLPs)

MLPs are the base of deep learning technology.
It belongs to a class of feed-forward neural networks having various
layers of perceptrons.

These perceptrons have various activation functions in them.

MLPs are mostly used to build image and speech recognition systems
or some other types of the translation software.
Autoencoders are mostly used as an unsupervised algorithm and its main use-
case is dimensionality reduction and compression. Their trick is that they try to
make the output equal to the input. In other works, they are trying to reconstruct
the data.

They consist of an encoder and a decoder. The encoder receives the input and it
encodes it in a latent space of a lower dimension. The decoder takes that vector
and decodes it back to the original input.

Train data and testing data ?

training data is the subset of original data that is used to train the machine learning model

testing data is used to check the accuracy of the model.

•The training dataset is generally larger in size compared to the testing dataset.
• The general ratios of splitting train and test datasets are 80:20, 70:30, or 90:10.
•Training data is well known to the model as it is used to train the model, whereas testing
data is like unseen/new data to the model.
Explain types of Learning ?

1.Supervised Machine Learning

2.Unsupervised Machine Learning
3.Semi-Supervised Machine Learning
4.Reinforcement Learning

Supervised Learning : Supervised machine learning is based on supervision. It means

in the supervised learning technique, we train the machines using the "labelled"
dataset, and based on the training, the machine predicts the output.
Some real-world applications of supervised learning are Risk Assessment, Fraud
Detection, Spam filtering, etc.

Unsupervised learning : It means, in unsupervised machine learning, the machine is

trained using the unlabeled dataset, and the machine predicts the output without any
supervision.

Semi supervised learning: Semi-Supervised learning is a type of Machine Learning

algorithm that lies between Supervised and Unsupervised machine learning uses the
combination of labelled and unlabeled datasets during the training period.

Reinforcement learning :Reinforcement learning works on a feedback-based process,

in which an AI agent (A software component) automatically explore its surrounding by
hitting & trail, taking action, learning from experiences, and improving its
performance.(Video games, robotics,text mining etc.)
. Explain overfitting ?
Overfitting is the main problem in the machine learning that degrades the performance of the machine learning training model.
Overfitting occurs when our machine learning model tries to cover all the data points or more than the required data points present in the
given dataset. Because of this, the model starts caching noise and inaccurate values present in the dataset, and all these factors reduce the
efficiency and accuracy of the model. The overfitted model has low bias and high variance.
Overfitting is the main problem that occurs in supervised learning.
1.Early Stopping,Train with more data,Feature Selection, Cross-Validation, Data Augmentation, Regularization
Explain three stages of building a machine learning model
A machine learning model is defined as a mathematical representation of the output of the training process.

How are Artificial Neural Networks different from Normal Computers?

How can we count the layers in a neural network?

Artificial Neural Networks have self-learning capabilities that
enable it to produce a better result as more data become
available.

The human brain can be defined as a neural network that is

made up of several neurons, so is the Artificial Neural Network
is made of numerous perceptron.