Book Image

Data Science with Python

By : Rohan Chopra, Aaron England, Mohamed Noordeen Alaudeen
Book Image

Data Science with Python

By: Rohan Chopra, Aaron England, Mohamed Noordeen Alaudeen

Overview of this book

Data Science with Python begins by introducing you to data science and teaches you to install the packages you need to create a data science coding environment. You will learn three major techniques in machine learning: unsupervised learning, supervised learning, and reinforcement learning. You will also explore basic classification and regression techniques, such as support vector machines, decision trees, and logistic regression. As you make your way through the book, you will understand the basic functions, data structures, and syntax of the Python language that are used to handle large datasets with ease. You will learn about NumPy and pandas libraries for matrix calculations and data manipulation, discover how to use Matplotlib to create highly customizable visualizations, and apply the boosting algorithm XGBoost to make predictions. In the concluding chapters, you will explore convolutional neural networks (CNNs), deep learning algorithms used to predict what is in an image. You will also understand how to feed human sentences to a neural network, make the model process contextual information, and create human language processing systems to predict the outcome. By the end of this book, you will be able to understand and implement any new data science algorithm and have the confidence to experiment with tools or libraries other than those covered in the book.
Table of Contents (10 chapters)

Adam Optimizer

Optimizers update weights with the help of loss functions. Selecting the wrong optimizer or the wrong hyperparameter for the optimizer can lead to a delay in finding the optimal solution for the problem.

The name Adam is derived from adaptive moment estimation. Adam has been designed specifically for training deep neural networks. The use of Adam is widespread in the data science community due to its speed in getting close to the optimal solution. Thus, if you want fast convergence, use the Adam optimizer. Adam does not always lead to the optimal solution; in such cases, SGD with momentum helps achieve state-of-the-art results. The following would be the parameters:

  • Learning rate: This is the step size for the optimizer. Larger values (0.2) result in faster initial learning, whereas smaller values (0.00001) slow the learning down during training.
  • Beta 1: This is the exponential decay rate for the mean estimates of the gradient.
  • Beta 2: This is the exponential decay...