Call Sales: +44(0)175 347 1040

Nvidia Powered
What is Deep Learning?

In recent years Deep Learning has become the most successful approach to pattern recognition for perceptual tasks. When you speak to Siri, Cortana, or Google Voice, your speech is being interpreted by a Deep Neural Network. And in the Large Scale Vision Recognition Challenge, Deep Neural Networks are outperforming humans at visual recognition tasks.

Deep Learning Brain

What is Deep Learning?

One step further to artificial intelligence

Deep learning is a term that covers a particular approach to building and training neural networks. One of the theoretical properties of neural networks that has kept researchers working on them is that they should be teachable. With most machine learning, the hard part is identifying the features in the raw input data, for example SIFT or SURF in images. Deep learning removes that manual step, instead relying on the training process to discover the most useful patterns across the input examples.

The classic example of deep learning is training a computer to be able to identify cats in a picture rather than dogs, with as much accuracy as a human – and beyond.

Contact Us

Deep Learning in a Nutshell

The basic idea is to train a very deep (i.e. lots of layers) neural network. Multiple studies have shown that neural networks, if appropriately configured, can reproduce any function (think universal Turing machines). However this doesn't mean that we know how to configure them. This is where Deep Learning comes in as by having lots and lots of layers a Deep Neural Network will solve a problem in lots of little steps, rather than in one or two big steps. While this may not seem such a revolutionary idea, it means that with a sufficiently large set of training data it is possible to train / configure these neural networks to solve tasks that have previously eluded us.

The Deep Learning Revolution

The machines are coming...

While all this is true, the training of Deep Neural Networks is computationally expensive, not only are the networks themselves very large but huge data sets are required to train them to a sufficient standard before they can be used on new data. Until recently we simply didn’t have the computational power, or access to the data required for Deep Learning to showcase what it can do. This has changed with the use of NVIDIA graphics cards for parallel programming and Deep Learning is now almost exclusively trained on GPUs, while the deployment of the resulting trained networks can be a relatively light load.

Once trained, never forgotten.

Nvidia Tesla Cards