An Introduction to Deep Learning and Keras
In this chapter, we will explore the field of deep learning (DL) with a brief introduction and then move to have a look at the popular choices of available frameworks for DL development. We will also take a closer look at the Keras ecosystem to understand
- PDF / 358,995 Bytes
- 16 Pages / 439.37 x 666.142 pts Page_size
- 41 Downloads / 245 Views
An Introduction to Deep Learning and Keras In this chapter, we will explore the field of deep learning (DL) with a brief introduction and then move to have a look at the popular choices of available frameworks for DL development. We will also take a closer look at the Keras ecosystem to understand why it is special and have a look at a sample code to understand how easy the framework is for developing DL models. Let’s get started.
Introduction to DL We’ll first start with a formal definition and then tackle a simple way of delineating the topic.
DL is a subfield of machine learning (ML) in artificial intelligence (AI) that deals with algorithms inspired from the biological structure and functioning of a brain to aid machines with intelligence.
© Jojo Moolayil 2019 J. Moolayil, Learn Keras for Deep Neural Networks, https://doi.org/10.1007/978-1-4842-4240-7_1
1
Chapter 1
An Introduction to Deep Learning and Keras
Maybe this was too high level or probably difficult to consume, so let’s break it down step by step. We see three important terms in the definition, in a specific order: DL, ML, and AI. Let’s first tackle these buzzwords individually, starting with AI.
Demystifying the Buzzwords AI in its most generic form can be defined as the quality of intelligence being introduced into machines. Machines are usually dumb, so to make them smarter we induce some sort of intelligence in them where they can take a decision independently. One example would be a washing machine that can decide on the right amount of water to use and on the required time for soaking, washing, and spinning; that is, it makes a decision when specific inputs are provided and therefore works in a smarter way. Similarly, an ATM could make a call on disbursing the amount you want with the right combination of notes available in the machine. This intelligence is technically induced in the machine in an artificial way, thus the name AI. Another point to note is that the intelligence here is explicitly programmed, say a comprehensive list of if-else rules . The engineer who designed the system carefully thought through all the combinations possible and designed a rule-based system that can make decisions by traversing through the defined rule path. What if we need to introduce intelligence in a machine without explicit programming, probably something where the machine can learn on its own? That’s when we touch base with ML.
Machine learning can be defined as the process of inducing intelligence into a system or machine without explicit programming. —Andrew NG, Stanford Adjunct Professor
2
Chapter 1
An Introduction to Deep Learning and Keras
Examples for ML could be a system that could predict whether a student will fail or pass in a test by learning from the historical test results and student attributes. Here, the system is not encoded with a comprehensive list of all possible rules that can decide whether a student will pass or fail; instead, the system learns on its own based on the patterns it learned from the historical data. So, w
Data Loading...
