To understand what a neural network is, it helps to first understand what machine learning is. Machine learning is a type of artificial intelligence where data is collected and used to understand the behavior of a particular process and then predict how that process will act in future settings as the system is continually fed new data. A neural network is a type of machine learning used for detecting patterns in unstructured data, such as images, transcriptions or sensor readings, for example.
“In neural networks, when data is collected about a particular process, the model that is used to learn about and understand that process and predict how that process will perform in the future is a simplified representation of how a brain neuron works,” said Mark Stadtmueller, vice president of product strategy at AI platform provider Lucd. “A brain neuron receives an input and based on that input, fires off an output that is used by another neuron. The neural network simulates this behavior in learning about collected data and then predicting outcomes.”
Related Article: Artificial Intelligence: Overhyped and Underappreciated
Neural Networks vs. Deep Learning
When the neural network has many layers, it is referred to as a deep neural network, or deep learning, Stadtmueller added. “The difference between a neural network and deep learning is that deep learning is the act of using a subset of neural networks called deep neural networks,” he said.
There are a number of scenarios in which deep learning is a preferable approach over using just neural networks. For example, when the datasets become exceedingly large, deep learning is advantageous because it can process more information and more complex information quickly and accurately, said Tim Hoolihan, senior director of Data Science and Analytics at call analytics startup DialogTech.
On the other hand, in certain scenarios deep neural networks are a better fit, such as with financial applications, according to Anna Knezevic, managing director of financial advisory firm M&A Solutions. She said that the company’s research and experience has been that using neural networks — as opposed to deep learning — creates a superior performance when predicting financial series like yield curves.
Indeed, many business applications rely solely on neural networks to solve complex problems. “Thanks to its ability to quickly categorize and recognize reams of information, virtually every tech titan — including Google, Microsoft and Amazon — is investing more in neural networks to solve various business problems,” said Nir Bar-Lev, co-founder and CEO of deep learning platform provider Allegro.ai.
Related Article: What Is Deep Learning and How Does it Relate to AI?
How Are Companies Using Neural Networks?
Companies are using neural networks in various ways, depending on their business model. “LinkedIn for instance, uses neural networks along with linear text classifiers to detect spam or abusive content in its feeds when it is created,” explained Deepak Agarwal, LinkedIn’s vice president of Artificial Intelligence. “We also use neural nets to help understand all kinds of content shared on LinkedIn — ranging from news articles to jobs to online classes — so we can build better recommendation and search products for members and customers.”
DialogTech uses neural networks to classify inbound calls into predetermined categories or to assign a lead quality score to calls, Hoolihan said. The neural network performs these actions based on the call transcriptions and the marketing channel or keyword that drove the call, he said. “For example, a caller who is speaking with a dental office may ask to ‘schedule an appointment.’ The neural network will seek, find and classify that phrase as a conversation, therefore providing marketers with valuable insights into the performance of marketing initiatives.”