Deep Learning vs Machine Learning

Machine Learning:

Machine Learning focuses on the development of algorithms and models that enable computers to learn
from data and make predictions or decisions without explicit programming. Here are key characteristics
of machine learning:

Feature Engineering: In machine learning, experts manually engineer or select relevant features from
the input data to aid the algorithm in making accurate predictions.

Supervised and Unsupervised Learning: Machine learning algorithms can be categorized into supervised
learning, where models learn from labeled data with known outcomes, and unsupervised learning,
where algorithms discover patterns and structures in unlabeled data.

Broad Applicability: Machine learning techniques find application across various domains, including
image and speech recognition, natural language processing, and recommendation systems.

Deep Learning:

Deep Learning is a subset of machine learning that focuses on training artificial neural networks inspired
by the human brain's structure and functioning. Here are key characteristics of deep learning:

Automatic Feature Extraction: Deep learning algorithms have the ability to automatically extract
relevant features from raw data, eliminating the need for explicit feature engineering.

Deep Neural Networks: Deep learning employs neural networks with multiple layers of interconnected
nodes (neurons), enabling the learning of complex hierarchical representations of data.

High Performance: Deep learning has demonstrated exceptional performance in domains such as
computer vision, natural language processing, and speech recognition, often surpassing traditional
machine learning approaches.

How Does Artificial Intelligence Work?

Put simply, AI systems work by merging large with intelligent, iterative processing algorithms. This
combination allows AI to learn from patterns and features in the analyzed data. Each time an Artificial
Intelligence system performs a round of data processing, it tests and measures its performance and uses
the results to develop additional expertise.

Ways of Implementing AI

Let’s explore the following ways that explain how we can implement AI:

Machine Learning

It is machine learning that gives AI the ability to learn. This is done by using algorithms to discover
patterns and generate insights from the data they are exposed to.

Deep Learning
Deep learning, which is a subcategory of machine learning, provides AI with the ability to mimic a human
brain’s neural network. It can make sense of patterns, noise, and sources of confusion in the data.

Here, we segregated the various kinds of images using deep learning. The machine goes through
multiple features of photographs and distinguishes them with feature extraction. The machine
segregates the features of each photo into different categories, such as landscape, portrait, or others.

Let us understand how deep learning works.

Input Layer

Hidden Layer

Output Layer

Input Layer

The images that we want to segregate go into the input layer. Arrows are drawn from the image on to
the individual dots of the input layer. Each of the white dots in the yellow layer (input layer) are a pixel
in the picture. These images fill the white dots in the input layer.

We should clearly know these three layers while going through this artificial intelligence tutorial.

Hidden Layer

The hidden layers are responsible for all our inputs' mathematical computations or feature extraction. In
the above image, the layers shown in orange represent the hidden layers. The lines that are seen
between these layers are called ‘weights’. Each one of them usually represents a float number, or a
decimal number, which is multiplied by the value in the input layer. All the weights add up in the hidden
layer. The dots in the hidden layer represent a value based on the sum of the weights. These values are
then passed to the next hidden layer.

You may be wondering why there are multiple layers. The hidden layers function as alternatives to some
degree. The more the hidden layers are, the more complex the data that goes in and what can be
produced. The accuracy of the predicted output generally depends on the number of hidden layers
present and the complexity of the data going in.

Output Layer

The output layer gives us segregated photos. Once the layer adds up all these weights being fed in, it'll
determine if the picture is a portrait or a landscape.

Example - Predicting Airfare Costs

This prediction is based on various factors, including:

Airline

Origin airport

Destination airport

Departure date
We begin with some historical data on ticket prices to train the machine. Once our machine is trained,
we share new data that will predict the costs. Earlier, when we learned about four kinds of machines,
we discussed machines with memory. Here, we talk about the memory only, and how it understands a
pattern in the data and uses it to make predictions for the new prices as shown below:

AI Programming Cognitive Skills: Learning, Reasoning and Self-Correction

Artificial Intelligence emphasizes three cognitive skills of learning, reasoning, and self-correction, skills
that the human brain possess to one degree or another. We define these in the context of AI as:

Learning: The acquisition of information and the rules needed to use that information.

Reasoning: Using the information rules to reach definite or approximate conclusions.

Self-Correction: The process of continually fine-tuning AI algorithms and ensure that they offer the most
accurate results they can.

However, researchers and programmers have extended and elaborated the goals of AI to the following:

Logical Reasoning

AI programs enable computers to perform sophisticated tasks. On February 10, 1996, IBM’s Deep Blue
computer won a game of chess against a former world champion, Garry Kasparov.

Knowledge Representation

Smalltalk is an object-oriented, dynamically typed, reflective programming language that was created to
underpin the “new world” of computing exemplified by “human-computer symbiosis.”

Planning and Navigation

The process of enabling a computer to get from point A to point B. A prime example of this is Google’s
self-driving Toyota Prius.

Natural Language Processing

Set up computers that can understand and process language.

Perception

Use computers to interact with the world through sight, hearing, touch, and smell.

Emergent Intelligence

Intelligence that is not explicitly programmed, but emerges from the rest of the specific AI features. The
vision for this goal is to have machines exhibit emotional intelligence and moral reasoning.

Some of the tasks performed by AI-enabled devices include:

Speech recognition

Object detection

Solve problems and learn from the given data