IT Brief Australia logo
Technology news for Australia's largest enterprises
Story image

Machine learning vs deep learning: what's the difference?

By Patrick Martlew
Tue 12 Dec 2017
FYI, this story is more than a year old

Article by Johanna Pingel, MathWorks product marketing manager.

Deep learning is getting lots of attention lately, and for good reason. It’s making a big impact in areas such as computer vision and natural language processing. It’s a key technology behind driverless cars, and voice control in consumer devices like phones and hands-free speakers.

What is deep learning?

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. Most deep learning methods use neural network architectures, which is why deep learning models are often referred to as deep neural networks.

The term “deep” usually refers to the number of hidden layers in the neural network. Traditional neural networks only contain 2-3 hidden layers, while deep networks can have as many as 150. One of the most popular types of deep neural networks is known as convolutional neural networks (CNN or ConvNet). A CNN convolves learned features with input data, and uses 2D convolutional layers, making this architecture well suited to processing 2D data, such as images.

Using an image example, a fully trained deep learning model will be able to automatically identify objects in images, even if it has never seen those exact images before. Ever wondered how certain websites can identify specific people in photos that were just uploaded? That’s deep learning at work.

Many of the techniques used in deep learning today have been around for decades. For example, deep learning has been used to recognise handwritten postal codes in the mail service since the 1990s.

Why has deep learning surged in popularity recently?

This main reason is accuracy. Deep learning models can achieve state-of-the-art accuracy, sometimes exceeding human-level performance. In addition, there are two main factors that have made these advances possible;

  1. Deep learning requires large amounts of labelled data. For example, driverless car development requires millions of images and thousands of hours of video. These large sets of labelled data are prevalent and have become available recently.

  2. Deep learning requires substantial computing power. High-performance GPUs have a parallel architecture that is efficient for deep learning. When combined with clusters or cloud computing, this enables development teams to reduce training time for a deep learning network from weeks to hours or less.

What is the difference between deep learning and machine learning?

Deep learning and machine learning both offer ways to train models and classify data. Let’s compare these two approaches to see what scenarios determine the use of each.

Using a standard machine learning approach, we would need to manually select the relevant features of an image, such as edges or corners, to train the machine learning model. The model then references these features when analysing and classifying new objects.

With a deep learning workflow, relevant features are automatically extracted from images. In addition, deep learning performs “end-to-end learning” – where a network is given raw data and a task to perform, such as classification, and it learns how to do this automatically.

Another key difference is deep learning algorithms scale with data, whereas shallow learning converges. Shallow learning refers to machine learning methods that plateau at a certain level of performance when you add more examples and training data to the network.

When choosing between machine learning and deep learning, we should ask ourselves whether we have a high-performance GPU and lots of labelled data. If we don’t have either of these things, we’ll have better luck using machine learning over deep learning.

This is because deep learning is generally more complex, so we need at least a few thousand images to get reliable results. We will also need a high-performance GPU so the model spends less time analysing all those images.

If we select machine learning, there is the option to train our model on many different classifiers. We might also know which features to extract that will produce the best results. Plus, with machine learning, we have the flexibility to choose a combination of approaches. Use different classifiers and features to see which arrangement works best for the data.

So, in general, deep learning is more computationally intensive, while machine learning techniques are often simpler to apply.

How is deep learning used in the real world?

Deep learning applications are used in many industries from automated driving to medical devices.

  • Automated Driving: Automotive researchers are using deep learning to automatically detect objects such as stop signs and traffic lights. In addition, deep learning is used to detect pedestrians, which helps decrease accidents.

  • Industrial Automation: Deep learning is helping to improve worker safety around heavy machinery by automatically detecting when people or objects are within an unsafe distance of machines.

  • Electronics: Deep learning is being used in automated hearing and speech translation. For example, home assistance devices that respond to your voice and know your preferences are powered by deep learning applications.

Deep learning often seems inaccessible to non-experts, but by exploring common deep learning workflows, engineers and scientists can now quickly and easily apply deep learning to their applications.

As deep learning becomes more ubiquitous, we will continue to see innovation and evolution in applications that were previously considered impossible across fields like computer vision, natural language processing, and robotics.

Related stories
Top stories
Story image
ChildFund
ChildFund launches new campaign to protect children online
ChildFund says WEB Safe & Wise aims to protect children from sexual exploitation and abuse online while also empowering them to become digitally savvy. 
Story image
Customer experience
Gartner recognises Okta for abilities in Access Management
Okta has announced it has been recognised as a Customers' Choice for the fourth time in a row in the Gartner Peer Insights "Voice of the Customer" report.
Story image
Data Protection
Barracuda launches new capabilities for API Protection
"Every business needs this type of critical protection against API vulnerabilities and automated bot attacks," Barracuda says.
Story image
Remote Working
Australia’s remote workers face connectivity and security issues
SOTI's new report finds better video conferencing technology and improved security measures are top concerns for remote workers in Australia.
Story image
Attain
Revenue operations is taking centre stage
As the business world continues to evolve, new demands need to be met to keep up with the ever-changing landscape. 
Story image
CRM
Zendesk announces new conversational CRM solutions
“The last few years have made it obvious that digital is the front door, convenience is paramount and relationships are anchored in conversations."
Story image
Supply chain
Jetstack promotes better security with supply chain toolkit
The web-based resource is designed to help organisations evaluate and plan the crucial steps they need to establish effective software supply chain security.
Story image
Customer experience
Research unveils precarious customer loyalty for retailers
New research has found customers are reassessing established brand loyalties as their priorities and behaviours shift.
Story image
Data solutions
South Australia state satellite makes significant progress
South Australia’s first state satellite has successfully completed the Critical Design Review (CDR), moving it closer to providing tangible data solutions.
Story image
Sisense
Data and analytics could be key to higher selling prices in APAC
Sisense's latest report has found that almost half of data professionals in APAC think customised data and analytics can create better selling prices for their products.
Story image
Qualys
Qualys updates Cloud Platform solution with rapid remediation
The new update is designed to enable organisations to fix asset misconfigurations, patch OS and third-party applications, and deploy custom software.
Story image
Artificial Intelligence
SAS announces new products amid cloud portfolio success
Analytics and AI company SAS is deepening its broad industry portfolio with offerings that support life sciences, energy, and martech.
Story image
Digital Transformation
How to modernise legacy apps without compromising security
At a time when digital transformation has become central to business, even the most important applications come with a ‘use-by’ date.
Story image
Ransomware
Cybersecurity starts with education
In 2021, 80% of Australian organisations responding to the Sophos State of Ransomware study reported being hit by ransomware. 
Story image
Sustainability
Grasping the opportunity to rethink the metrics of a sustainable data centre
A data centre traditionally has two distinct operations teams: the Facility Operations team, and the IT Operations team. Collaboration between them is the key to defining, measuring, and delivering long-term efficiency and sustainability improvements.
Story image
Amazon Web Services / AWS
RedShield leverages AWS to scale cybersecurity services
"Working with AWS gives RedShield the ability to mitigate significant application layer DDoS attacks, helping leaders adopt best practices and security architectures."
Story image
Excel
Could your Excel practices be harming your business?
While Excel has been the de-facto standard for budgeting, planning, and forecasting, is it alone, enough to support organisations in the global marketplace that’s facing rapid changes due to digital transformation?
Story image
Cloud Security
Aqua Security createa unified scanner for cloud native security
“By integrating more cloud native scanning targets into Trivy, such as Kubernetes, we are simplifying cloud native security."
Story image
Ransomware
A third of companies paying ransom don’t recover data - report
Veeam's report finds 76% of businesses who are victims of cyberattacks paid the ransom to recover data, but a third were still unable to get their information back.
Story image
Application Security
What are the DDoS attack trend predictions for 2022?
Mitigation and recovery are vital to ensuring brand reputation remains solid in the face of a Distributed Denial of Service (DDoS) attack and that business growth and innovation can continue.
Story image
Data Center
Preventing downtime costs and damage with Distributed Infrastructure Management
Distributed Infrastructure Management (DIM) can often be a lifeline for many enterprises that work with highly critical ICT infrastructure and power sources.
Story image
SaaS
Rubrik Security Cloud marks 'next frontier' in cybersecurity
"The next frontier in cybersecurity pairs the investments in infrastructure security with data security giving companies security from the point of data."
Story image
Digital Transformation
The impact of COVID-19 on healthcare environments and care delivery
The COVID-19 pandemic has revolutionised the healthcare industry while overcoming staff shortages, social distancing requirements, and lockdowns.
Story image
Cybersecurity
Managed service providers: effective scoping to avoid costly vendor pitfalls
Managed security services are outsourced services focusing on the security and resilience of business networks.
Story image
Cybersecurity
Hard numbers: Why ambiguity in cybersecurity no longer adds up
As cybersecurity costs and risks continue to escalate, CEOs continue to struggle with what their investment in cyber protection buys. Getting rid of ambiguity becomes necessary.
Story image
Apple
Apple previews new features for users with disabilities
Apple says new software features that offer users with disabilities new tools for navigation, health and communication, are set to come out later this year.
Story image
Artificial Intelligence
How to ensure ethical deployment of AI implementations
The increase in automation and machine technology such as AI and machine learning has unlocked a whole new level of scale and service to organisations. 
Story image
Artificial Intelligence
CFOs using digital workers and AI to prevent unnecessary loss
New technology is now allowing CFOs to use digital workers to automate their accounting processes, making it easier for them to avoid unnecessary losses.
Story image
Telstra
Telstra, Google and Accenture launch 5G AR experience for AFL
Telstra, Google and Accenture are developing a new 5G powered augmented reality (AR) experience at Melbourne's Marvel Stadium for the footy season.
Exabeam
Find out how a behavioural analytics-driven approach can transform security operations with the new Exabeam commissioned Forrester study.
Link image
Story image
Alteryx
Decision Inc. Australia enters partnership with Alteryx
Independent data and analytics consultancy Decision Inc. Australia has partnered with automated analytics company Alteryx, expanding its offering to clients.
Story image
Remote Working
How zero trust and SD-WANs can support productive remote working
The way people connect with applications and data has changed, users are remotely accessing resources that could be stored anywhere from a corporate data center to the cloud.
Story image
Infrastructure
Nutanix study reveals financial services sector lagging with multicloud adoption
Nutanix has released new research that reveals the financial services sector is lagging behind when it comes to multicloud adoption.
Story image
Cybersecurity
The 'A-B-C' of effective application security
Software applications have been a key tool for businesses for decades, but the way they are designed and operated has changed during the past few years.
Story image
Sift
Sift shares crucial advice for preventing serious ATO breaches
Are you or your business struggling with Account Takeover Fraud (ATO)? One of the latest ebooks from Sift can provide readers with the tools and expertise to help launch them into the new era of account security.
Darktrace
Threat actors are exploiting weaknesses in interconnected IT/OT ecosystems. Darktrace illuminates your entire business and takes targeted action to stop emerging attacks.
Link image
Story image
Cybersecurity
A10 Networks finds over 15 million DDoS weapons in 2021
A10 Networks notes that in the 2H 2021 reporting period, its security research team tracked more than 15.4 million Distributed Denial-of-Service (DDoS) weapons.
Story image
Wireless
Cradlepoint expands its Cellular Intelligence capabilities
Cradlepoint has announced additional Cellular Intelligence capabilities with its NetCloud service.
Story image
Apricorn
Data backup plans inadequate, data still at risk - study
The Apricorn 2022 Global IT Security Survey revealed that while the majority organisations have data backup plans in place, data for many are at risk.
Story image
Sustainability
Power at the edge: the role of data centers in sustainability
The Singaporean moratorium on new data center projects was recently lifted, with one of the conditions being an increased focus on power efficiency and sustainability.
Story image
Manufacturing
HINDSITE wins Aerospace Xelerated Pitch Challenge with solution to support Boeing
Brisbane-based startup HINDSITE was the winner of the first ever Pitch Challenge organised by Aerospace Xelerated in partnership with Queensland XR Hub. 
Softiron
For every 10PB of storage run on HyperDrive vs. comparable alternatives, an estimated 6,656 tonnes of CO₂ are saved by reduced energy consumption alone over its lifespan. That’s the equivalent of taking nearly 1,500 cars off the road for a year.
Link image
Story image
Microsoft
New Relic enters multi-year partnership with Microsoft Azure
New Relic has announced a strategic partnership with Microsoft to help enterprises accelerate cloud migration and multi-cloud initiatives. 
Story image
Cybersecurity
Infoblox's State of Security Report spotlights Australian remote work hazards
Attackers exploit weak WiFi, remote endpoints, and the cloud, costing 50% of organisations over $1.3 million in breach damages.