Technical Strategy for AI Engineers, in The Era of Deep Learning.
Publisher:- Rahul Kumar Sharma.
The term machine learning was first coined in the 1950s when Artificial Intelligence frontiersperson Arthur Samuel built the first self-learning system for playing checkers. He detected that the more the system played, the better it served.
Fueled by advances in statistics and computer science, as nicely as better datasets and the growth of neural webs, machine learning has truly taken off in recent years.
Today, whether you recognize it or not, machine learning is everywhere ‒ automated translation, image recognition, spokesperson search technology, self-driving cars, and beyond.
In this manual, we’ll explain how machine learning works and how you can use it in your business. We’ll also teach you to machine learning tools.
In This E-Book we learn about these kinds of topics
1. Why Machine Learning Strategy
Machine learning is the basis of countless important applications, including web search, email anti-spam, speech recognition, product recommendations, and more. I think that you or your team is working on a machine learning application and that you want to make rapid progress. This book will allow you to do so.
2. How to use this book to help your team
After completing this book, you will have a deep understanding of how to set up a technical manager for a machine learning project. But your teammates might not understand why you’re advising a particular direction. Maybe you want your team to define a single-number evaluation metric, but they aren’t convinced.
3. Prerequisites and Notation
If you have taken a Machine Learning course such as my machine learning MOOC on Coursera, or if you have an understanding of applying supervised learning, you will be able to understand this text. I assume you are friendly with supervised learning: learning a function that maps from x to y, using tagged training examples (x,y). Supervised knowledge algorithms include linear regression, logistic regression, and neural networks. There are multiple forms of machine learning, but the majority of Machine Learning’s practical worth today comes from supervised learning.
4. Scale drives machine learning progress
Many of the concepts of deep learning (neural networks) have been around for decades. Why are these ideas carrying off now? Two of the biggest drivers of recent improvement have been:
- Data availability:- People are now spending additional time on digital devices (laptops, mobile devices). Their digital actions generate huge amounts of data that we can provide to our learning algorithms.
- Computational scale:- We started just a few years ago to be able to train neural networks that are large enough to take advantage of the huge datasets we now control.
5. Your development and test sets
Let’s return to our earlier cat pictures example: You run a mobile app, and users are uploading pictures of many additional things to your app. You want to automatically discover the cat pictures. Your group gets a large training set by downloading pictures of cats (positive examples) and non-cats (negative examples) from other websites. They separated the dataset 70%/30% into training and test sets. Using this data, they build a cat detector that performs well on the training and test sets.