M. Tim Jones, veteran embedded firmware architect explains, Deep builds on the ideas of neural networks by increasing their scope, basic algorithms and depth.
Artificial intelligence (AI) has suffered through decades of
unrealistic expectations followed by disappointment and subsequent
changes in research direction. These AI winters were necessary to alter
the direction of research to more promising ideas, resulting in an AI
spring.
Deep learning came about roughly 20 years ago. It built on the ideas
of neural networks by increasing their scope, basic algorithms, and
their depth. The introduction of deep neural networks has created a
revolution that powers self-driving vehicles, giving machines the
ability to describe the contents of images, and much more. This
article explores the origins of deep learning, the architectures of deep
neural networks, and the current state-of-the-art use cases. It also
introduces the frameworks used to create deep neural networks that are
accessible to anyone.
What Is Deep Learning?
Deep learning is a subfield of
machine learning (ML) and represents a set of neural network
architectures that solves complex, cutting-edge problems. These
architectures (or models) go by the names convolutional neural networks
(CNNs) and long short-term memory (LSTM), among others...
Deep Learning vs. Neural Networks
A key differentiating feature
of deep neural networks is depth: the number of layers in addition to
the breadth or number of processing elements within each layer. But,
deep neural networks have evolved from the typical multilayer networks
that brought us to the point of deep learning. The architectures of deep
neural networks are different from their multilayer ancestors. CNNs,
which work well with image data, sample and pool pixels from the image
for processing. RNNs, which are ideal for sequence data such as text,
consider not just an input but the inputs that precede and follow it...
Conclusion
As a set of architectures that are advancing the
state of the art in many application areas, deep learning has brought a
resurgence of interest in ML. Peripheral industries have also taken
note, and hardware and software technologies are advancing to bring deep
learning to new classes of devices and applications. Deep learning
frameworks are also making these architectures more accessible and
popular.
Read more...
Source: Toolbox