Artificial Intelligence and Machine Learning:

The application of “machine learning” and “artificial intelligence” has become popular within the last decade. Both terms are frequently used in Computer science and social media, sometimes interchangeably, sometimes with different meanings. In it, we aim to clarify the relationship between these terms and, in particular, to specify the contribution of machine learning to artificial intelligence.

Machine Learning Definition :

Machine learning is an application of artificial intelligence that provides systems the ability to automatically learn and improve from experience without being explicitly programmed.

In general, we can differentiate between unsupervised and supervised machine learning. Machine learning focuses on the development of computer programs that can access data and use it learn for themselves. Machine learning describes a set of techniques that are commonly used to solve a variety of real-world problems with the help of computer systems which can learn to solve a problem instead of being explicitly programmed

Artificial Intelligence Definition:

The theory and development of computer systems able to perform tasks normally requiring human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages.

Artificial intelligence in healthcare

Artificial intelligence (AI) in healthcare is the use of complex algorithms and software to emulate human cognition in the analysis of complicated medical data. Specifically, AI is the ability of computer algorithms to approximate conclusions without direct human input.

Artificial intelligence algorithms are generally grouped into three categories. These are Supervised Learning, Unsupervised Learning, and Reinforcement Learning. Unsupervised Learning case, target output is not given, and the model is expected to form a template from the given inputs.

Artifical Neural Network :

An artificial neural network is an interconnected group of nodes, inspired by a simplification of neurons in a brain. Here, each circular node represents an artificial neuron and an arrow represents a connection from the output of one artificial neuron to the input of another.

We explain also in series this topic.

Artificial Intelligence uses

Currently AI is Used is Following Things/Fields:

·        Virtual Assistant or Chatbots.

·        Agriculture and Farming.

·        Autonomous Flying.

·        Retail, Shopping and Fashion.

·        Security and Surveillance.

·        Sports Analytics and Activities.

·        Manufacturing and Production.

·        Live Stock and Inventory Management.

Machine Learning Types :

The learning backend dictates first if the intelligent agent is able to learn, and, second, how the agent is able to learn, e.g., which precise algorithms it uses, what type of data processing is applied, how concept drift is handled, etc.

Machine Learning Algorithms:

List of Common Machine Learning Algorithms :

·      Linear Regression

·      Logistic Regression

·      Decision Tree

·      SVM

·      Naive Bayes

·      kNN

·      K-Means

·      Random Forest

·      Dimensionality Reduction Algorithms

·      Gradient Boosting algorithms

Machine Learning Vs Deep Learning

The difference between deep learning and machine learning

In practical terms, Deep learning is just a subset of machine learning. In fact, deep learning technically is machine learning and functions in a similar way. However, its capabilities are different. While basic machine learning models do become progressively better at whatever their function is, they still need some guidance. If an AI algorithm returns an inaccurate prediction, then an engineer has to step in and make adjustments. With a deep learning model, an algorithm can determine on its own if a prediction is accurate or not through its own neural network.

Machine learning vs Artificial Intelligence :

• Practically: Machine Learning and AI are used interchangeably. Usually both terms are used to mean supervised learning.
• Theoretical: Machine Learning is a subfield of AI: One way of implementing AI.

Different meanings to different people

A big part of the confusion is that – depending on who you talk to – Machine Learning and AI mean different things to different users.

In Media & Marketing: Everything is AI

AI is a more sexy term than Machine Learning right now, so in media & marketing, the term Artificial Intelligence (AI) is used most often. But the range of things the media refers to as AI is very wide:

• Expert Systems
• Process Automation
• Machine Learning
• Deep Learning
• Reinforcement Learning

Machine Learning Applications

1.Machine Learning Applications in Social Media

In this day and age, who doesn’t use Social Media?!! And social media platforms like Twitter, Facebook, LinkedIn, etc. are the first names that pop out while thinking about social media. Well, guess what! A lot of the features in these platforms that mystify you are actually actually achieved using Machine Learning.

Machine Learning Datasets :

These datasets are used for machine-learning research and have been cited in peer-reviewed academic journals. High-quality labeled training datasets for supervised and semi-supervised machine learning algorithms are usually difficult and expensive to produce because of the large amount of time needed to label the data.

Machine Learning Decision Tree:

A tree has many analogies in real life, and turns out that it has influenced a wide area of machine learning, covering both classification and regression. In decision analysis, a decision tree can be used to visually and explicitly represent decisions and decision making. As the name goes, it uses a tree-like model of decisions. Though a commonly used tool in data mining for deriving a strategy to reach a particular goal, its also widely used in machine learning

Machine Learning vs Data Science:

Data Science vs. Machine Learning. At its core, data science is a field of study that aims to use a scientific approach to extract meaning and insights from data. Machine learning, on the other hand, refers to a group of techniques used by data scientists that allow computers to learn from data.

Regression in Machine Learning

Machine Learning Regression

Linear Regression is a machine learning algorithm based on supervised learning. ... Linear regression performs the task to predict a dependent variable value (y) based on a given independent variable (x). So, this regression technique finds out a linear relationship between x (input) and y(output).

Machine Learning Methods :

The ten methods described offer an overview — and a foundation you can build on as you hone your machine learning knowledge and skill:

1.   Regression

2.   Classification

3.   Clustering

4.   Dimensionality Reduction

5.   Ensemble Methods

6.   Neural Nets and Deep Learning

7.   Transfer Learning

8.   Reinforcement Learning

9.   Natural Language Processing

10.       Word Embeddings