What is Deep Learning ?

Introduction

          Arivon Technologies enables to explore the latest trends on Artificial Intelligence Applications and utilize the maximum benefits of this Technology. Please visit www.arivontech.com   for more details. Contact us sales@arivontech.com  .

AI – Importance of Deep learning                                          

·  Deep learning is a machine learning technique that learns features and tasks directly from data. Data can be images, text, or sound.

·    Deep learning offen referred to as end-to-end learning.

·    Deep learning is a sub-field of machine learning.

·   Deep Learning means using a neural network with several layers of nodes between input and output .

What is deep learning?

·    Neural networks are a beautiful biologically-inspired programming paradigm which enables a computer to learn from data. These are learning algorithms.

·     Deep learning is a powerful set of techniques for learning using neural networks.

·    Neural networks and deep learning currently provide the best solutions to many problems in image recognition, speech recognition, and natural language processing.

·   If you provide the system plenty of information, it begins to understand it and respond in useful ways.

   How deep learning works?

• ·    Deep learning is a form of machine learning that uses a model of computing that’s very much inspired by the structure of the brain.
• ·     Deep Learning is a machine learning method. It allows us to train an AI to predict outputs, given a set of inputs. Both supervised and unsupervised learning can be used to train the AI.

   Neural networks:

              Let’s look inside the brain of our AI.

·   Like animals, our estimator AI’s brain has neurons. These neurons are inter-connected.

·   A method of computing, based on the interaction of multiple connected processing elements.

·    Ability to learn from experience in order to improve their performance.

·    A powerful technique to solve many real world problems.

·  A neural network is a combination of many neurons where the dendrite of  one neuron is connected to the axon of other neuron.

                                                  Fig : Different types of layers

The neurons are grouped into three different types of layers:

1. Input Layer
2. Hidden Layer(s)
3. Output Layer

• The input layer receives input data. The input layer passes the inputs to the first hidden layer. The input layer nodes are passive, doing nothing but relaying the values from their single input to their multiple outputs.
• The hidden layers perform mathematical computations on our inputs. The main aim of creating the neural networks is to decide the number of hidden layers, in addition to the number of neurons for each layer.
• The “Deep” in Deep Learning refers to having more than one hidden layer.

Conclusion:

• ·      Access to more computational power in the cloud, advancement of sophisticated algorithms, and the availability of funding are unlocking new possibilities.
• ·    Unimaginable just five years ago. But it’s the availability of new, rich data sources that is making deep learning real.
• ·         Manually designed features are always incomplete and takes more time to design.