What is Deep Learning? Learn The Basics in 5 Mins

Last Updated January 10, 2021

Deep learning is a subset of machine learning, and the methodology is actually modelled around the human brain.

In technical terms, our neurons connect to each other through electrical and chemical activations, filtering out different inputs through our dendrites, soma and axons 

It sounds complicated because, well, it is. But we promise to keep it as simple as possible. 

Deep Learning Essentials 

For starters, to allow a machine to learn like we do, it needs information like we do.  

Consider the file deep_learning_cat.jpg posted below.  

The machine uses a set of “neurons” in its artificial neural network to analyze the image.

Each neuron analyzes a different aspect of the file, and the machine will check if the image reaches a favorable result. If not, it will shift the importance it places on the results of a specific neuron over another. 

This is often referred to as weight.  

By putting weight on each neuron, it understands better which aspects will be more important to analyze when looking for this deep_learning_cat.jpg. 

These weights are generated randomly, and much like evolution, the deep learning machine goes through many mutations to reach its “optimal” point.  

This machine then becomes proficient at identifying cats.  

These neural networks need to have several layers to accomplish anything meaningful. These layers are what makes this form of machine learning “deep.”  

Confused yet? That’s ok. Just read the next section and it will all make sense. 

How Humans ‘Deep Learn’

Answering “What is deep learning?” becomes easier when using the most familiar examples: humans.  

We have been deep learning since we arrived in this world, without ever realizing how cool it is.  

Attempting to explain how the brain works is a lot harder because to most of us it really ‘just works.’ Muscle memory is where it gets to be more relatable.  

Don’t Fret – Deep Learning Explained

Imagine you’re learning how to play the guitar. You press down on the strings, attempting to form a G chord, only to strum it out of tune and have it gone flat halfway through. With practice, you will get better as your muscle memory will start to retain certain information.  

How important is the amount of pressure I place on the strings? The position of my arms? The speed of my strum? The curvature of my fingers? 

As you play more, this practice will create a subconscious memory of what is happening, and you place weights on what matters more, focusing on certain things over others.  

deep learning guitar

For example, there would be a lot of importance on your eyes looking at the frets of the guitar when you start, but with more experience that becomes less important since your hand can go into perfect position without looking.  

One human may need 50 practice rounds while the other may need 500, but one can argue that with enough practice any healthy human can produce a perfect G chord. 

The Weight of Deep Learning 

Now, equate this human importance to the machine’s weighting. The machine would shift its weighting just like we shift our importance – placing a high weight on the factors that are more likely to accomplish the task and a low weight for the factors that don’t tend to help the machine accomplish the task. 

Let’s look at identifying cats again. One feature that might be important in looking for cats is the eyes, meaning the eye identifier would have a high weight. A less important feature might be the color of the fur, meaning a low weight for the fur identifier.  

The machine would reach this conclusion after many random selections of weights, altering weights slightly less and less the more likely their current weighting is positively contributing to a specific goal. 

When you went through your impromptu guitar lesson moments ago, you practiced playing the G chord a thousand times before retaining some muscle memory. A machine needs practice too, so we feed it big chunks of data before it goes from doing something right 0.01% of the time to doing it right 99.99% of the time – not 100% because there is always room for error. 

Where do machines find their data to practice? 

Machines find the data needed to practice through the developer’s creation of a data inventory.  

In most cases, this task is very hands on and depends on the data you need. The more innovative technology gets, the more likely it is the data doesn’t exist and needs to be collected. 

With the creation of the desired data inventory, the deep learning machine can start running. As we watch it learn more and more, we anticipate the day that machines learn as fast as – or faster than – us. 

We Can Get the Data to Train Your AI 

Summa Linguae Technologies is an experienced localization solutions service provider that is also taking the lead in speech, image, and video data collection for emerging technologies at scale. 

We collect a wide variety of data for AI-powered products, including voice assistants, chatbots, autonomous vehicles, and more. 

Our data solutions team is recognized by our clients to be extremely versatile with our outside-of-the-box thinking. 

Contact us today to discuss how we can meet your speech data needs. 

Related Posts

Summa Linguae uses cookies to allow us to better understand how the site is used. By continuing to use this site, you consent to this policy.

Learn More