Deep Learning

Your constantly-updated definition of Deep Learning and collection of videos and articles
169 shares

What is Deep Learning?

Show Hide video transcript
  1. Transcript loading…

Deep learning is a type of machine learning that uses layers of artificial neural networks to mimic the behavior of the human brain. Each synthetic neuron is very simple, but the vast numbers used create powerful data structures.

They can be used to process unstructured input of various types, primarily images and text. The deep learning algorithms identify features of interest and, in so doing, assign weights to each of the artificial neurons involved. The weights are adjusted as more input data is processed, with the successively refined results being described as learning. The style of learning can take several forms: supervised, unsupervised and reinforcement, depending on the nature of any feedback provided during training.

Some of the most popular forms of artificial intelligence rely on deep learning, including chatbots, virtual assistants and self-driving cars.

Neural Networks

Neural networks for deep learning have several hidden layers between input and output at the extremities. This is the origin of the term "deep".

© Interaction Design Foundation, CC BY-SA 4.0

Neural networks consist of interconnected artificial neurons similar in structure to the human brain. Deep learning uses layers of these networks to discover patterns in data and make decisions based on them. Unlike earlier forms of machine learning, pattern discovery in neural networks is learned rather than programmed. This can lead to the unfortunate consequence that it is not always clear how predictions have been derived.

Deep Learning vs Machine Learning

Although deep learning is a form of machine learning, there are some important differences.

Deep learning…

  • Is trained using large amounts of data.

  • Makes use of feedback in the environment, including past mistakes.

  • Works with unstructured data, for example, images, text and audio.

  • Can discover complex, non-linear relationships in the data.

  • Needs large numbers of GPUs (graphics processing units) that specialize in parallel processing.

Machine learning …

  • Can work with smaller data sets.

  • Requires more human intervention to correct and improve the algorithms.

  • Often needs additional pre- and post-processing to handle unstructured data.

  • Is more simplistic in terms of the relationships it can discover in the data.

  • Does not rely on parallel processing so can be trained with conventional CPUs (central processing units).

History of Deep Learning

The concept of artificial neurons, which are fundamental to deep learning, was first proposed in the 1940s by McCulloch and Pitts (see the illustration below). However, deep learning itself did not get much attention until later in the 20th century, when some breakthroughs were made in…

  • Recurrent neural networks: A type of network that uses the output of one pass as the input to the next, making them recursive or recurrent. This approach is important in language processing since the meaning of a sentence is dependent on the sequence of words.

  • Convolutional neural networks: A system for feature recognition loosely based on the visual processing of the human brain.

  • Backpropagation: Adjusting the weights in a neural network based on the error rate of the previous pass.

In the early 21st century, advances in speech, language and image processing made deep learning possible. The availability of large datasets also contributed to the training of neural networks which underpin deep learning algorithms. More recently, advances in parallel processing, in the form of Graphical Processing Units (GPUs), significantly reduced the time taken for training neural networks on very large datasets. Originally, these would have been the same GPUs found in gaming cards, but versions specialized for neural networks have since been developed.

Diagram of a human neuron. Signals are received through the dendrites (left) and sent out through the axon (right).

CC BY-SA 4.0 ShareAlike (https://creativecommons.org/licenses/by-sa/4.0/)

A graphic representation of the McCulloch-Pitts neuron. Signals are received by g (left). f (right) makes a decision whether to provide an output. All signals are binary (either 0 or 1).

© Interaction Design Foundation, CC BY-SA 4.0

Deep learning is now receiving significant attention, with applications in many fields. It is constantly improving and is making substantial contributions to artificial intelligence generally, as described below.

Applications of Deep Learning

Chatbots

Using neural networks, chatbots can convincingly mimic human conversation. In February 2024, researchers established that some were indistinguishable from humans by passing the Turing test. (The test was devised by Alan Turing in 1950 to measure the "intelligence" of machines.)

Chatbots can learn from interactions with people or from other sources, such as the vast body of conversations found on the World Wide Web. They can understand natural language and produce meaningful responses. Modern deep-learning chatbots are very sophisticated and can process complex questions and instructions. They learn from interactions over time and improve themselves when made aware of mistakes.

A chatbot explaining how they learn.

Microsoft Copilot, Fair Use

Virtual Assistants

Amazon Echo Dot with Alexa virtual assistant.

Virtual assistants (VAs) like Alexa, Google Assistant and Siri increasingly use deep learning to perform complex tasks. These include understanding spoken language, generating responses and learning from user feedback. Some related applications, such as Google Lens, use deep learning for image processing and object recognition. We are likely to see similar features built into virtual assistants as the technology improves.

Self-Driving Cars

Self-driving cars use deep learning.

In many respects, self-driving cars act as virtual assistants (see above) but require additional capabilities to deal with the complexities of driving itself:

  • Computer vision: Deep learning enables self-driving cars to analyze images and videos and provide relevant information or actions based on them. For example, modern cars process road signs to establish speed limits. Self-driving cars go further, using deep learning algorithms to identify important objects such as pedestrians and other vehicles.

  • End-to-end learning: Self-driving cars use deep learning to enhance their understanding of the environment by taking advantage of raw sensor data, such as camera images. Otherwise, they would need to rely on pre-programmed features or extra stages of processing.

Learn More about Deep Learning

Questions about Deep Learning

What is deep learning AI?

Deep learning AI is a type of artificial intelligence that uses artificial neural networks to learn from data and perform tasks that require human-like intelligence, such as image recognition, natural language processing, and speech recognition.

What is deep learning?

Deep learning is a subset of machine learning that uses neural networks with multiple layers to analyze complex patterns and relationships in data. It is inspired by the structure and function of the human brain and has been successful in a variety of tasks, such as computer vision, natural language processing, and speech recognition.

How does deep learning work?

In deep learning, a computer model learns to perform classification tasks directly from images, text, or sound. Deep learning models can achieve state-of-the-art accuracy, sometimes exceeding human-level performance. Models are trained by using a large set of labeled data and neural network architectures that contain many layers.

How is deep learning different from machine learning?

Deep learning differs from machine learning in the type of data that it works with and the methods that it uses to learn. Machine learning algorithms leverage structured, labeled data to make predictions, while deep learning algorithms can ingest and process unstructured data, such as text and images, and automate feature extraction. Machine learning algorithms typically require more human intervention to correct and learn, while deep learning algorithms can learn independently from the environment and past mistakes.

Does ChatGPT use deep learning?

Yes, ChatGPT uses deep learning to generate human-like text. It uses the transformer architecture, a type of neural network that has been successful in various natural language processing tasks and is trained on a massive corpus of text data from the internet.

What is deep learning used for?

Deep learning is used for many applications that require human-like intelligence, such as image recognition, natural language processing, speech recognition, sentiment analysis, recommendation systems, self-driving cars, fraud detection, medical diagnosis, and many more.

What does batch size mean in deep learning?

Batch size is a hyperparameter that defines the number of samples used in one iteration of training a deep learning model. The choice of batch size can have a significant impact on the performance of the model, such as its accuracy, speed, memory usage, and generalization ability.

What is transfer learning in deep learning?

Transfer learning is a technique in which a model trained on one task is used as a starting point for training a model on a different but related task. It applies the weights of the learned features to the new model. The pre-trained model serves as transferred knowledge to be applied in another domain.

Where is deep learning used?

Deep learning is used in various domains and industries that require intelligent solutions, such as healthcare, finance, retail, transportation, education, entertainment, security, agriculture, manufacturing, and many more.

What is the difference between deep learning and neural networks?

Deep learning can handle more complex and unstructured data, such as images, text, and speech, and automate feature extraction. Neural networks are algorithms that mimic the way the biological neurons in the human brain work. Neural networks are simpler and more limited in their capabilities, while deep learning models are more complex and can handle more complex data sets.

Answer a Short Quiz to Earn a Gift

Question 1

What distinguishes deep learning from traditional machine learning?

1 point towards your gift

Question 2

What challenge do designers face when training deep learning models?

1 point towards your gift

Question 3

How has deep learning revolutionized image and video analysis?

1 point towards your gift

Question 4

Which area benefits significantly from deep learning?

1 point towards your gift

Question 5

What risk should designers address when they implement deep learning?

1 point towards your gift

Better luck next time!

0 out of 5 questions answered correctly

Do you want to improve your UX / UI Design skills? Join us now

Congratulations! You did amazing

5 out of 5 questions answered correctly

You earned your gift with a perfect score! Let us send it to you.

Letter from IxDF

Check Your Inbox

We’ve emailed your gift to name@email.com.

Do you want to improve your UX / UI Design skills? Join us now

Literature on Deep Learning

Here’s the entire UX literature on Deep Learning by the Interaction Design Foundation, collated in one place:

Learn more about Deep Learning

Take a deep dive into Deep Learning with our course AI for Designers .

In an era where technology is rapidly reshaping the way we interact with the world, understanding the intricacies of AI is not just a skill, but a necessity for designers. The AI for Designers course delves into the heart of this game-changing field, empowering you to navigate the complexities of designing in the age of AI. Why is this knowledge vital? AI is not just a tool; it's a paradigm shift, revolutionizing the design landscape. As a designer, make sure that you not only keep pace with the ever-evolving tech landscape but also lead the way in creating user experiences that are intuitive, intelligent, and ethical.

AI for Designers is taught by Ioana Teleanu, a seasoned AI Product Designer and Design Educator who has established a community of over 250,000 UX enthusiasts through her social channel UX Goodies. She imparts her extensive expertise to this course from her experience at renowned companies like UiPath and ING Bank, and now works on pioneering AI projects at Miro.

In this course, you’ll explore how to work with AI in harmony and incorporate it into your design process to elevate your career to new heights. Welcome to a course that doesn’t just teach design; it shapes the future of design innovation.

In lesson 1, you’ll explore AI's significance, understand key terms like Machine Learning, Deep Learning, and Generative AI, discover AI's impact on design, and master the art of creating effective text prompts for design.

In lesson 2, you’ll learn how to enhance your design workflow using AI tools for UX research, including market analysis, persona interviews, and data processing. You’ll dive into problem-solving with AI, mastering problem definition and production ideation.

In lesson 3, you’ll discover how to incorporate AI tools for prototyping, wireframing, visual design, and UX writing into your design process. You’ll learn how AI can assist to evaluate your designs and automate tasks, and ensure your product is launch-ready.

In lesson 4, you’ll explore the designer's role in AI-driven solutions, how to address challenges, analyze concerns, and deliver ethical solutions for real-world design applications.

Throughout the course, you'll receive practical tips for real-life projects. In the Build Your Portfolio exercises, you’ll practice how to integrate AI tools into your workflow and design for AI products, enabling you to create a compelling portfolio case study to attract potential employers or collaborators.

All open-source articles on Deep Learning

Please check the value and try again.

Open Access—Link to us!

We believe in Open Access and the democratization of knowledge. Unfortunately, world-class educational materials such as this page are normally hidden behind paywalls or in expensive textbooks.

If you want this to change, , link to us, or join us to help us democratize design knowledge!

Share Knowledge, Get Respect!

Share on:

or copy link

Cite according to academic standards

Simply copy and paste the text below into your bibliographic reference list, onto your blog, or anywhere else. You can also just hyperlink to this page.

Interaction Design Foundation - IxDF. (2023, October 26). What is Deep Learning?. Interaction Design Foundation - IxDF.

New to UX Design? We're Giving You a Free eBook!

The Basics of User Experience Design

Download our free ebook “The Basics of User Experience Design” to learn about core concepts of UX design.

In 9 chapters, we’ll cover: conducting user interviews, design thinking, interaction design, mobile UX design, usability, UX research, and many more!

A valid email address is required.
315,329 designers enjoy our newsletter—sure you don’t want to receive it?