Deep Learning is the most recent buzzword – which covers most of the Research in todays world. Starting from Image Processing, Vision, Social Network Analysis, Text Analysis, Deep Learning – had taken the show.

This blog mainly covers:

1. Introduction of Artificial Intelligence

2. Relation of Machine Learning with Deep Learning

3. Artificial Neural Networks

4. ML Vs DL

5. DL Neural Network Architecture

6. What is TensorFlow?

**Artificial Intelligence**

As the human – have deductive reasoning, inference and decision-making so does the computer which is still a long time away, but One thing that have been remarkable gains in the application of AI techniques and associated algorithms.<img

**A Deeper Dive into Deep Learning**

The Input data is transformed throughout the layers of a deep learning neural network by artificial neurons or processing units. The chain of transformations that occur from input to output is known as the Credit Assignment Path (CAP).

The CAP value is the measurement or concept of ‘depth’ in a deep learning model architecture. According to Wikipedia, most researchers in the field agree that deep learning has multiple nonlinear layers with a CAP greater than two, and some consider a CAP greater than ten to be very deep learning.

Some of the different deep-learning model architectures and learning algorithms include:

Feed-forward neural networks
Recurrent neural network
Multi-layer Perceptrons (MLP)
Convolutional neural networks
Recursive neural networks
Deep belief networks
Convolutional deep belief networks
Self-Organizing Maps
Deep Boltzmann machines
Stacked de-noising auto-encoders
It’s worth pointing out that due to the relative increase in complexity, deep learning and neural network algorithms can be prone to Over-fitting. In addition, increased model and algorithmic complexity can result in very significant computational resource and time requirements.

It’s also important to consider that solutions may represent local minima as opposed to a global optimal solution. This is due to the complex nature of these models when combined with optimization techniques such as gradient descent.

### Like this:

Like Loading...