Goto

Collaborating Authors

Overfitting and Resampling Techniques in Machine Learning

#artificialintelligence

When a model – instead of learning generalizable features – approximates the patients in the training set too closely, it is said to be „overfitted" to the training set. This means that, while the model may demonstrate high performance when making predictions on the patients it was trained on, its performance on new patients will be far poorer because the model has not in fact extracted generalizable rules for prediction. Instead, it has learnt the characteristics of the training set patients by heart. In this situation, the model demonstrates minimal bias (erroneous assumptions) and high variance (sensitivity to small fluctuations). Overfitting can be diagnosed by comparing training error with out-of-sample error (OSE) – if training set error is much lower than OSE, a model is said to overfit.


Augmented Reality Is Coming -- to Your Car's Windshield

#artificialintelligence

Like millions of other kids around the world, Jamieson Christmas, now in his mid-forties, was transfixed the first time he saw director George Lucas' epic space opera Star Wars. "I'm a child of the '70s," he told Digital Trends. "I grew up when Star Wars was first released. George Lucas set up this vision of little robots beaming three-dimensional pictures of people. It had a really tremendous influence on me."


You can help a Mars Rover's AI learn to tell rocks from dirt – TechCrunch

#artificialintelligence

Mars Rover Curiosity has been on the Red Planet for going on eight years, but its journey is nowhere near finished -- and it's still getting upgrades. You can help it out by spending a few minutes labeling raw data to feed to its terrain-scanning AI. Curiosity doesn't navigate on its own; there's a whole team of people on Earth who analyze the imagery coming back from Mars and plot a path forward for the mobile science laboratory. In order to do so, however, they need to examine the imagery carefully to understand exactly where rocks, soil, sand and other features are. This is exactly the type of task that machine learning systems are good at: You give them a lot of images with the salient features on them labeled clearly, and they learn to find similar features in unlabeled images.


The role of data in industry 4.0 - Connected Technology Solutions

#artificialintelligence

The challenges encountered by manufacturing companies when it comes to handling data are well reported, but what can they do to ensure that data is an asset rather than a problem? Data has long been treated in the manufacturing industry as the orphan nephew living in the cupboard under the stairs. While operational and service industries have leapt on the benefits of data as the catalyst of business growth and efficiency gains, the manufacturing sector has been slow to adopt the culture of becoming a data-driven business. According to Accenture, only 13 per cent of manufacturing companies have seen through a digital transformation of their processes. "In many ways the core approach to manufacturing has remained unchanged for the past 50 years despite the industry experimenting with offshoring and integrated manufacturing in mega factories," Tim Hall, VP products, InfluxData, says.


The 2020 data and AI landscape

#artificialintelligence

When COVID hit the world a few months ago, an extended period of gloom seemed all but inevitable. Yet many companies in the data ecosystem have not just survived but in fact thrived. Perhaps most emblematic of this is the blockbuster IPO of data warehouse provider Snowflake that took place a couple of weeks ago and catapulted Snowflake to a $69 billion market cap at the time of writing – the biggest software IPO ever (see the S-1 teardown). And Palantir, an often controversial data analytics platform focused on the financial and government sector, became a public company via direct listing, reaching a market cap of $22 billion at the time of writing (see the S-1 teardown). Meanwhile, other recently IPO'ed data companies are performing very well in public markets. Datadog, for example, went public almost exactly a year ago (an interesting IPO in many ways, see my blog post here).


How Data Catalogs Expand Discovery and Improve Governance

#artificialintelligence

AI and automation are making it easier for users to find the data they need. Those of us beyond a certain age remember when school research projects began in front of the library card catalog: that now-antique set of wooden cabinets with the long drawers full of well-thumbed cards that adhered to a standard bibliographic system. If you understood that system (or had the help of a good librarian), you could perform a surprising amount of research at a metadata level before having to hunt through the library stacks for the actual books you needed. You could use the system to understand relationships between book topics and perhaps discover an unexpected book that was perfect for your report. Library catalogs, along with an increasing number of pre-digital-age storage systems, have changed.


5 Reasons Why We Need Explainable Artificial Intelligence

#artificialintelligence

This might be the first time you hear about Explainable Artificial Intelligence, but it is certainly something you should have an opinion about. Explainable AI (XAI) refers to the techniques and methods to build AI applications that humans can understand "why" they make particular decisions. In other words, if we can get explanations from an AI system about its inner logic, this system is considered as an XAI system. Explainability is a new property that started to gain popularity in the AI community, and we will talk about why that happened in recent years. Let's dive into the technical roots of the problem, first.


How AI Voice Assistants Can Revolutionize Health

#artificialintelligence

The vision for this future is to unlock the human voice as a meaningful measurement of health. AI voice assistants can transform speech into a vital sign, enabling early detection and predictions of oncoming conditions. Similar to how temperature is an indicator of fever, vocal biomarkers can provide us with a more complete picture of our health. One in four people globally will be affected by major or minor mental health issues at some point in their lives. Around 450 million people currently suffer from conditions such as anxiety, stress, depression, or others, placing mental health among the leading cause of ill-health worldwide.


Is Artificial Intelligence Closer to Common Sense?

#artificialintelligence

Artificial intelligence researchers have not been successful in giving intelligent agents the common-sense knowledge they need to reason about the world. Without this knowledge, it is impossible for intelligent agents to truly interact with the world. Traditionally, there have been two unsuccessful approaches to getting computers to reason about the world--symbolic logic and deep learning. A new project, called COMET, tries to bring these two approaches together. Although it has not yet succeeded, it offers the possibility of progress.


Is Artificial Intelligence Closer to Common Sense?

#artificialintelligence

Artificial intelligence researchers have not been successful in giving intelligent agents the common-sense knowledge they need to reason about the world. Without this knowledge, it is impossible for intelligent agents to truly interact with the world. Traditionally, there have been two unsuccessful approaches to getting computers to reason about the world--symbolic logic and deep learning. A new project, called COMET, tries to bring these two approaches together. Although it has not yet succeeded, it offers the possibility of progress.