Develop-Packt
Change the repository type filter
All
Repositories list
160 repositories
- Understand how supervised and unsupervised machine learning methods can be used to construct and implement a text classifier in Python.
- Learn how to collect, clean and categorize data for your projects. Then extract the key textual features and present them visually.
- Understand what vectors are, and how they can be used to compare the frequencies of words and similar documents, and group them accordingly.
- Discover the basic tools and techniques required to preprocess data to use in an NLP project.
- Explore the libraries and frameworks used to perform sentiment analysis on textual data.
- Learn about various Topic Modeling algorithms, and how to apply them to datasets. Compare the strengths of different algorithms with some practical challenges.
- Generate and paraphrase text using different models for use in Python. Understand the applications and challenges of text summarization models.
- Collect data by scraping web pages, then analyze your findings. Learn how to use APIs to retrieve real-time data from Twitter.
- This module covers handling new data and creating a model that can learn continuously from the patterns and help make better predictions.
- This module covers the basics components of a neural network and its essential operations. It also explores a trained neural network created using TensorFlow
- This module discusses the current state of reinforcement learning and describes some promising approaches being taken to advance the field.
- This module introduces the architecture of CNN and explains how to implement it to develop image classifiers from scratch
Neural-Networks
PublicThis module will introduce you to Artificial Neural Networks and a practical approach to build single and multilayer neural networks to solve supervised learning tasksAdvanced-RNNs
PublicThis module covers the implementation of advanced RNN models that overcome the drawbacks of plain RNNs. We will particularly look at LSTM, GRU-based model, Bi-directional and Stacked RNNs.- This module demonstrates the power of word embeddings and explains the popular deep learning-based approaches for embeddings
- The module covers the theory behind reinforcement learning and introduces Markov chains and Markov Decision Processes
- In this module you will learn about Generative Adversarial Networks (GAN) and their basic components along with some of the use cases of GAN.
- This chapter introduces you to two types of supervised learning algorithms in detail. The first algorithm will help us to classify data points using decision trees, while the other algorithm will help us classify using random forests.
- This module introduces you to the fundamentals of Artificial Intelligence. You will be implementing your first AI through a simple Tic-Tac-Toe game where you will be teaching the program on how to win against a human player
- In this chapter you will be introduced to the final topic on neural networks and deep learning. You will come across TensorFlow, Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). You will also be implementing an image classification program using neural networks and deep learning
- This module provides you with a good understanding what deep learning is and how programming with TensorFlow works
- This module looks at policy based methods of reinforcement learning, principally the drawbacks to value based methods like Q learning that motivate the use of policy gradients.
- This module explores how important Recurrent Neural Networks (RNNs) are for sequence modeling. It particularly focuses on deep learning approaches for sequences, particularly plain RNNs and 1D convolutions Foundations more advanced RNN-based models are laid in this module
- This module discusses the motivation for evolutionary strategies, and breaks down the components of genetic algorithms and how they can be tailored for reinforcement learning.
Clustering-Fundamentals
PublicThis chapter will get you introduced to the fundamentals of Clustering which will be illustrated with two unsupervised learning algorithms. You will be implementing flat clustering with the k-means algorithm and hierarchical clustering with the mean shift algorithm. By the end of this chapter you will have a firm grasp on the basics of Clustering.- This module introduces classification — you will be implementing the various techniques such as k-nearest neighbors and Support Vector Machines. You will be using the Euclidean distance to work with the k-nearest neighbors.
- In this module you will be introduced to regression which plays an important role while it comes to prediction of the future by using the past historical data. You will come across various techniques such as Linear regression with one and multiple variables, along with polynomial and Support Vector Regression
- Explore basic machine learning algorithms and learn to build, train, and evaluate Artificial Neural Networks in Keras.
- Briefly review the foundational components of data wrangling and Python data structures.