Deep Learning

By Lucine Avanesian


What is deep learning?

Deep learning is a machine learning technique that allows computers to learn by example in the same way that humans do. Deep learning is a critical component of self-driving automobiles, allowing them to detect a stop sign or discriminate between a pedestrian and a lamppost. It is essential for voice control in consumer electronics including phones, tablets, and televisions.


A computer model learns to execute categorization tasks directly from images, text, or sound in deep learning. Deep learning models can attain state-of-the-art accuracy, even surpassing human performance in some cases. Models are trained utilising a huge quantity of labelled data and multilayer neural network topologies.


How does it work?

Deep learning models are sometimes referred to as deep neural networks because most deep learning approaches use neural network designs. The number of hidden layers in a neural network is commonly referred to as "deep." Deep neural networks can have up to 150 hidden layers, whereas traditional neural networks only have 2-3. Large sets of labelled data and neural network topologies that learn features directly from the data without the requirement for manual feature extraction are used to train deep learning models.


Figure 1: Neural networks, which are organized in layers consisting of a set of interconnected nodes. Networks can have tens or hundreds of hidden layers.


What is deep learning used for?

  • Electronics: In automatic hearing and voice translation, deep learning is applied. Deep learning applications, for example, are used to power home help gadgets that respond to your voice and remember your preferences.

  • Medical Research: Deep learning is being used by cancer researchers to detect cancer cells automatically. UCLA researchers developed a high-dimensional data set that was used to train a deep learning application to reliably identify cancer cells.

  • Automated Driving: Deep learning is being used by automotive researchers to detect items such as stop signs and traffic lights automatically. Deep learning is also utilised to recognise pedestrians, which reduces the number of collisions.



Works Cited

What is deep learning?: How it works, techniques & applications. How It Works, Techniques

& Applications - MATLAB & Simulink. (n.d.). Retrieved October 9, 2021, from

https://www.mathworks.com/discovery/deep-learning.html.


By: IBM Cloud Education. (n.d.). What is deep learning? IBM. Retrieved October 9, 2021,

from https://www.ibm.com/cloud/learn/deep-learning.


Brownlee, J. (2020, August 14). What is deep learning? Machine Learning Mastery.

Retrieved October 9, 2021, from

https://machinelearningmastery.com/what-is-deep-learning/.



10 views0 comments

Recent Posts

See All