# Deep Learning / Neural Networks In Machine Learning

In this blog, we will learn some important facts or topics which is related to deep learning which is given below:

In this, we will cover some important and useful topics which are listed below.

Recommendation systems

Deep Classifiers

DeepFace

TensorFlow

Keras

LSTMs

CNNs

__Recommender System__

__Recommender System__

This is a top useful machine learning application which is used for predicting the future preference of a set of items for a user and recommend the top items.

Let us suppose the real-life example like Netflix, it is a collection of a large number of movies then a new problem arose as people had a hard time selecting the items they actually want to see.

To overcome this problem the recommender system is used.

Methods used to build the recommender system

**Content-based recommendation****Collaborative Filtering**

**Machine Learning ****Classifiers**

**Machine Learning**

**Classifiers**

There are different types of classifiers, a classifier is an algorithm that maps the input data to a specific category. Now, let us take a look at the different types of classifiers:

Perceptron

Naive Bayes

Decision Tree

Logistic Regression

K-Nearest Neighbor

Artificial Neural Networks/Deep Learning

Support Vector Machine

__DeepFace Recognition In Machine Learning__

__DeepFace Recognition In Machine Learning__

It is a facial recognition system, which is used by Facebook for tagging images. It was proposed by researchers at *Facebook AI Research (FAIR)* at the *2014 IEEE Computer Vision and Pattern Recognition Conference (CVPR)*.

Below the four steps which are used to a recognition of face:

Detect

Align

Represent

Classify

__TensorFlow__

__TensorFlow__

TensorFlow is an open-source machine learning framework. It is used for implementing machine learning and deep learning applications. It is created by the Google team for developing and research an idea on AI.

To designed the TensorFlow the python programming language is used hence it makes it easy to use.

Some of the key features of TensorFlow are:

Efficiently works with mathematical expressions involving multi-dimensional arrays

Good support of deep neural networks and machine learning concepts

GPU/CPU computing where the same code can be executed on both architectures

High scalability of computation across machines and huge data sets

** Installing **TensorFlow

__using “pip”__

`pip install tensorflow`

__Importing ____TensorFlow__

`import tensorflow as tf`

**Example: **To calculate a simple linear function.

```
import tensorflow as tf
x = tf.constant(-2.0, name="x", dtype=tf.float32)
a = tf.constant(5.0, name="a", dtype=tf.float32)
b = tf.constant(13.0, name="b", dtype=tf.float32)
y = tf.Variable(tf.add(tf.multiply(a, x), b))
init = tf.global_variables_initializer()
with tf.Session() as session:
session.run(init)
print(session.run(y))
```

__Keras __

__Keras__

If you know the other two important python library “Theano” and “TensorFlow” then we will now learn another important library which is used in python machine learning is “Keras”

It is a deep learning library that can run on top of Theano or TensorFlow.

It runs on both It runs on Python 2.7 or 3.5 and executes on GPUs and CPUs.

It installs using pip:

`sudo pip install keras`

It makes simple Keras model with few lines of code so it is better than other libraries like “TensorFlow” or “Theano”

__Example:__

```
from keras.models import Sequential
from keras.layers import Dense, Activation
model = Sequential()
model.add(Dense(64, activation='relu', input_dim=50)) #input shape of 50
model.add(Dense(28, activation='relu')) #input shape of 50
model.add(Dense(10, activation='softmax'))
```

__LSTMs__

__LSTMs__

This is the new technology of deep learning **artificial neural network(ANNs)**

Convolutional Neural Networks (CNNs)

Long Short-Term Memory (LSTM)

Long Short Term Memory networks – usually just called “LSTMs” – are a special kind of RNN, capable of learning long-term dependencies. They were introduced by Hochreiter & Schmidhuber (1997). LSTMs are explicitly designed to avoid the long-term dependency problem.

LSTMs also have this chain-like structure, but the repeating module has a different structure. Instead of having a single neural network layer, there are four, interacting in a very special way.

__Source__

__CNNs__

__CNNs__

Convolutional neural network (CNNs) is one of the main categories of deep learning neural network which is used to images recognition, images classifications. Objects detections, recognition faces, etc., are some of the areas where CNNs are widely used.

It also called ConvNet.

Contact us for this machine learning assignment Solutions by Codersarts Specialist who can help you mentor and guide for such machine learning assignments.

If you have project or assignment files, You can send at **contact@codersarts.com**__ __ directly