Skip to content

Latest commit

 

History

History
41 lines (29 loc) · 4.02 KB

README.md

File metadata and controls

41 lines (29 loc) · 4.02 KB

Deep Learning

Deep learning is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example. Deep learning is a key technology behind driverless cars, enabling them to recognize a stop sign, or to distinguish a pedestrian from a lamppost. It is the key to voice control in consumer devices like phones, tablets, TVs, and hands-free speakers. Deep learning is getting lots of attention lately and for good reason. It’s achieving results that were not possible before.

Why Deep Learning Matters?

Some examples from the Real World Industry emphasize the importance of Deep Learning.

  • Automated Driving:

    It is one of the inital and most common fields that have devevloped thanks to several crucial advancements in DL. The following link can used to get some of the latest advancements in Self-Driving Cars Self Driving Cars, IEEE Spectrum

  • Aerospace and Defence

  • Medical Research

  • Industrial Automation

And several others applications in numerous small scale to large scale industries.

How Deep Learning Works?

Deep Learning is heavily dependent upon Neural Network Architectures and hence refered to as Deep Neural Networks. Basic Neural Networks look like, Neural Network Image

Source: in.mathworks.com

Traditionally Neural Networks contain about 2-3 hidden layers and additional input and output layers. But Deep Learning Networks have around 150 hidden layers which make a bit difficult to train but achieve high accuracy and optimal results.

Difference between ML and DL

Deep learning is a machine learning technique that is inspired by the way a human brain filters information. It helps a computer model to filter the input data through layers to predict and classify information. Since deep learning processes information in a similar manner as a human brain does, it is mostly used in applications that people generally do.

Another key difference is deep learning algorithms scale with data, whereas shallow learning converges. Shallow learning refers to machine learning methods that plateau at a certain level of performance when you add more examples and training data to the network.

A key advantage of deep learning networks is that they often continue to improve as the size of your data increases.

While Machine Learning is a subset of Artificial Intelligence that uses statistical learning algorithms to build systems that have the ability to automatically learn and improve from experiences without being explicitly programmed.

Resources to Get you Started:

  • Courses:

    • Deep Learning Specilaization, Coursera : This is one of the most popular and community-loved specialization that offers a plethora of choices to the student. It provides a basic foundation to most of the concepts in Deep Learning and contains Five Courses that can be audited separately if the reader is interested in a specific field, namely,

      • Neural Networks and Deep Learning - Introductory Course.
      • Improving the Deep Neural Networks using Hyperparameter Tuning and other Optimization Techniques. - Intermediate Level Course focused for optimization problems.
      • CNN and RNNs - For Image Processing and Natural Language Processing

    • Introduction To Deep Learning, MIT: For students who prefer the traditional way of learning via classroom lectures.

    • Deep Learning For Engineers, Matlab : For the people who are experinced with concepts of DL and would like to implement them using Matlab.