4 In broad strokes, three kinds of learnings models are often used in machine learning:

4.1 Supervised learning

is a machine learning model that maps a specific input to an output using labeled training data (structured data). In simple terms, to train the algorithm to recognize pictures of cats, feed it pictures labeled as cats.

4.2 Unsupervised learning

is a machine learning model that learns patterns based on unlabelled data (unstructured data). Unlike supervised learning, the end result is not known ahead of time.
Rather, the algorithm learns from the data, categorizing it into groups based on attributes. For instance, unsupervised learning is good at pattern matching and descriptive modeling.
In addition to supervised and unsupervised learning, a mixed approach called semi-supervised learning is often employed, where only some of the data is labeled. In semi-supervised learning, an end result is known, but the algorithm must figure out how to organize and structure the data to achieve the desired results.

4.4 Reinforcement learning

is a machine learning model that can be broadly described as “learn by doing.” An “agent” learns to perform a defined task by trial and error (a feedback loop) until its performance is within a desirable range.
The agent receives positive reinforcement when it performs the task well and negative reinforcement when it performs poorly. An example of reinforcement learning would be teaching a robotic hand to pick up a ball.

pagetop

5 Common types of artificial neural networks

5.1 Artificial neural network

A common type of training model in AI is an artificial neural network, a model loosely based on the human brain.

5.2 A neural network

is a system of artificial neurons—sometimes called perceptrons—that are computational nodes used to classify and analyze data. more
The data is fed into the first layer of a neural network, with each perceptron making a decision, then passing that information onto multiple nodes in the next layer.
Training models with more than three layers are referred to as “deep neural networks” or “deep learning.”
Some modern neural networks have hundreds or thousands of layers.
The output of the final perceptrons accomplish the task set to the neural network, such as classifying an object or find patterns in data.

6 Some of the most common types of artificial neural networks you may encounter include:

6.1 Feedforward neural networks (FFNN)

are one of the oldest forms of neural networks, with data flowing one way through layers of artificial neurons until the output is achieved.
In modern days, most feedforward neural networks are considered “deep feedforward” with several layers (and more than one “hidden” layer).
Feedforward neural networks are typically paired with an error-correction algorithm called “backpropagation” * that, in simple terms, starts with the result of the neural network and works back through to the beginning, finding errors to improve the accuracy of the neural network. Many simple but powerful neural networks are deep feedforward.
* Backpropagation, short for "backward propagation of errors," is a fundamental algorithm used to train artificial neural networks, enabling them to learn by adjusting weights based on the error between predicted and actual outputs.

6.2 Recurrent neural networks (RNN)

differ from feedforward neural networks in that they typically use time series data or data that involves sequences.
Unlike feedforward neural networks,
which use weights in each node of the network, recurrent neural networks have “memory” of what happened in the previous layer as contingent to the output of the current layer.
For instance, when performing natural language processing, RNNs can “keep in mind” other words used in a sentence. RNNs are often used for speech recognition, translation, and to caption images.

6.3 Long/short term memory (LSTM)

is an advanced form of RNN that can use memory to “remember” what happened in previous layers.
The difference between RNNs and LSTM is that LSTM can remember what happened several layers ago, through the use of “memory cells.”
LSTM is often used in speech recognition and making predictions.

pagetop

6.4 Convolutional neural networks (CNN)

include some of the most common neural networks in modern artificial intelligence.
Most often used in image recognition, CNNs use several distinct layers (a convolutional layer, then a pooling layer) that filter different parts of an image before putting it back together (in the fully connected layer).
The earlier convolutional layers may look for simple features of an image, such as colors and edges, before looking for more complex features in additional layers.

6.5 Generative adversarial networks (GAN)

involve two neural networks competing against each other in a game that ultimately improves the accuracy of the output.
One network (the generator) creates examples that the other network (the discriminator) attempts to prove true or false.
GANs have been used to create realistic images and even make art.

7 Benefits of AI

7.1 Automation

AI can automate workflows and processes or work independently and autonomously from a human team.
For example, AI can help automate aspects of cybersecurity by continuously monitoring and analyzing network traffic.
Similarly, a smart factory may have dozens of different kinds of AI in use, such as robots using computer vision to navigate the factory floor or to inspect products for defects, create digital twins, or use real-time analytics to measure efficiency and output.

7.2 Reduce human error

AI can eliminate manual errors in data processing, analytics, assembly in manufacturing, and other tasks through automation and algorithms that follow the same processes every single time.

7.3 Eliminate repetitive tasks

AI can be used to perform repetitive tasks, freeing human capital to work on higher impact problems.

AI can be used to automate processes, like verifying documents, transcribing phone calls, or answering simple customer questions like “what time do you close?”

Robots are often used to perform “dull, dirty, or dangerous” tasks in the place of a human.

7.4 Fast and accurate

AI can process more information more quickly than a human, finding patterns and discovering relationships in data that a human may miss.

7.5 Infinite availability

AI is not limited by time of day, the need for breaks, or other human encumbrances. When running in the cloud, AI and machine learning can be “always on,” continuously working on its assigned tasks.

pagetop

7.6 Accelerated research and development

The ability to analyze vast amounts of data quickly can lead to accelerated breakthroughs in research and development. For instance, AI has been used in predictive modeling of potential new pharmaceutical treatments, or to quantify the human genome.

Speech recognition
Automatically convert spoken speech into written text.
Image recognition
Identify and categorize various aspects of an image.
Translation
Translate written or spoken words from one language into another.
Predictive modeling
Mine data to forecast specific outcomes with high degrees of granularity.
Data analytics
Find patterns and relationships in data for business intelligence.
Cybersecurity
Autonomously scan networks for cyber attacks and threats.
Related products and services

7.8 AI algorithms and models.

Google offers a number of sophisticated artificial intelligence products, solutions, and applications on a trusted cloud platform that enables businesses to easily build and implement AI algorithms and models.
By using products like Vertex AI, CCAI, DocAI, or AI APIs, organizations can make sense of all the data they’re producing, collecting, or otherwise analyzing, no matter what format it’s in, to make actionable business decisions.

4 In broad strokes, three kinds of learnings models are often used in machine learning:

4.1 Supervised learning

is a machine learning model that maps a specific input to an output using labeled training data (structured data). In simple terms, to train the algorithm to recognize pictures of cats, feed it pictures labeled as cats.

4.2 Unsupervised learning

is a machine learning model that learns patterns based on unlabelled data (unstructured data). Unlike supervised learning, the end result is not known ahead of time.

Rather, the algorithm learns from the data, categorizing it into groups based on attributes. For instance, unsupervised learning is good at pattern matching and descriptive modeling.

4.4 Reinforcement learning

is a machine learning model that can be broadly described as “learn by doing.” An “agent” learns to perform a defined task by trial and error (a feedback loop) until its performance is within a desirable range.

The agent receives positive reinforcement when it performs the task well and negative reinforcement when it performs poorly. An example of reinforcement learning would be teaching a robotic hand to pick up a ball.

pagetop

5 Common types of artificial neural networks

5.1 Artificial neural network

A common type of training model in AI is an artificial neural network, a model loosely based on the human brain.

5.2 A neural network

is a system of artificial neurons—sometimes called perceptrons—that are computational nodes used to classify and analyze data. more

The data is fed into the first layer of a neural network, with each perceptron making a decision, then passing that information onto multiple nodes in the next layer.

Training models with more than three layers are referred to as “deep neural networks” or “deep learning.”

Some modern neural networks have hundreds or thousands of layers.

The output of the final perceptrons accomplish the task set to the neural network, such as classifying an object or find patterns in data.

6 Some of the most common types of artificial neural networks you may encounter include:

6.1 Feedforward neural networks (FFNN)

are one of the oldest forms of neural networks, with data flowing one way through layers of artificial neurons until the output is achieved.

In modern days, most feedforward neural networks are considered “deep feedforward” with several layers (and more than one “hidden” layer).

* Backpropagation, short for "backward propagation of errors," is a fundamental algorithm used to train artificial neural networks, enabling them to learn by adjusting weights based on the error between predicted and actual outputs.

6.2 Recurrent neural networks (RNN)

differ from feedforward neural networks in that they typically use time series data or data that involves sequences.

Unlike feedforward neural networks,

which use weights in each node of the network, recurrent neural networks have “memory” of what happened in the previous layer as contingent to the output of the current layer.

For instance, when performing natural language processing, RNNs can “keep in mind” other words used in a sentence. RNNs are often used for speech recognition, translation, and to caption images.

6.3 Long/short term memory (LSTM)

is an advanced form of RNN that can use memory to “remember” what happened in previous layers.

The difference between RNNs and LSTM is that LSTM can remember what happened several layers ago, through the use of “memory cells.”

LSTM is often used in speech recognition and making predictions.

pagetop

6.4 Convolutional neural networks (CNN)

include some of the most common neural networks in modern artificial intelligence.

Most often used in image recognition, CNNs use several distinct layers (a convolutional layer, then a pooling layer) that filter different parts of an image before putting it back together (in the fully connected layer).

The earlier convolutional layers may look for simple features of an image, such as colors and edges, before looking for more complex features in additional layers.

6.5 Generative adversarial networks (GAN)

involve two neural networks competing against each other in a game that ultimately improves the accuracy of the output.

One network (the generator) creates examples that the other network (the discriminator) attempts to prove true or false.

GANs have been used to create realistic images and even make art.

7 Benefits of AI

7.1 Automation

7.2 Reduce human error

AI can eliminate manual errors in data processing, analytics, assembly in manufacturing, and other tasks through automation and algorithms that follow the same processes every single time.

7.3 Eliminate repetitive tasks

AI can be used to perform repetitive tasks, freeing human capital to work on higher impact problems.

AI can be used to automate processes, like verifying documents, transcribing phone calls, or answering simple customer questions like “what time do you close?”

Robots are often used to perform “dull, dirty, or dangerous” tasks in the place of a human.

7.4 Fast and accurate

AI can process more information more quickly than a human, finding patterns and discovering relationships in data that a human may miss.

7.5 Infinite availability

AI is not limited by time of day, the need for breaks, or other human encumbrances. When running in the cloud, AI and machine learning can be “always on,” continuously working on its assigned tasks.

pagetop

7.6 Accelerated research and development

The ability to analyze vast amounts of data quickly can lead to accelerated breakthroughs in research and development. For instance, AI has been used in predictive modeling of potential new pharmaceutical treatments, or to quantify the human genome.

Speech recognition

Automatically convert spoken speech into written text.

Image recognition

Identify and categorize various aspects of an image.

Translation

Translate written or spoken words from one language into another.

Predictive modeling

Mine data to forecast specific outcomes with high degrees of granularity.

Data analytics

Find patterns and relationships in data for business intelligence.

Cybersecurity

Autonomously scan networks for cyber attacks and threats.

Related products and services

7.8 AI algorithms and models.

Google offers a number of sophisticated artificial intelligence products, solutions, and applications on a trusted cloud platform that enables businesses to easily build and implement AI algorithms and models.

By using products like Vertex AI, CCAI, DocAI, or AI APIs, organizations can make sense of all the data they’re producing, collecting, or otherwise analyzing, no matter what format it’s in, to make actionable business decisions.

---------------------

Contact