Develop-Packt's repositories
Deep-Neural-Networks-with-Keras
Experiment with Neural Network architectures to build and evaluate both single and multi-layer sequential models in Keras
Introduction-to-Artificial-Neural-Networks
This module describes a step-by-step method to solve a supervised learning classification problem using a neural network and analyzes the results of the neural network by performing error analysis.
Introduction-to-Machine-Learning-Models
Learn to compare, contrast, and apply different types of machine learning algorithm. Also analyze overfitting and implement regularization and solve real-world problems using the machine learning algorithms.
t-Distributed-Stochastic-Neighbor-Embedding
You will learn to implement t-SNE models in scikit-learn and explain the limitations of t-SNE. Being able to abstract high-dimensional information into lower dimensions will prove helpful for visualization and exploratory analysis, as well as in conjunction with the clustering algorithms. By the end of this course, you will be able to find clusters in high-dimensional data, such as user-level information or images.
Analytics-Using-Complex-Data-Types
This module covers performing descriptive analytics on time series data, geospatial data, complex data types (arrays, JSON, and JSONB), and text.
Applications-in-Business-Use-Cases
Fix, clean, merge, and connect new data to perform data wrangling tasks on UN and GDP data
Becoming-Pythonic
Discover what it means to be "Pythonic", learn to write succinct, readable expressions for creating lists; use Python comprehensions with lists, dictionaries, and sets.
Building-Artificial-Neural-Networks-in-Keras
Review the mathematics that comprise Artificial Neural Networks, apply linear transformations in Python, and build a logistic regression model with Keras
Computer-Vision-with-Convolutional-Neural-Networks
Explore the architecture of CNNs and related techniques to build image processing applications and classify models with Keras
Constructing-Python-Classes-and-Methods
Discover classes in Python, one of the cornerstones of object-oriented programming. Also explore how to use methods in Python programming.
Dimensionality-Reduction-Techniques-and-PCA
In this course, you will apply dimension reduction techniques and describe the concepts behind principal components and dimensionality reduction. This course teaches you how to apply Principal Component Analysis (PCA) when solving problems using scikit-learn. By the end of this course, you will be able to reduce the size of a dataset by extracting only the most important components of variance within the data.
Discovering-Tools-for-Python-Developers
Learn to write Python collaboratively as a member of a team; use conda to document and set up the dependencies for your Python programs; use Docker to create reproducible Python environments to run your code.
Executing-Python-Programs-Algorithms-and-Functions
Explore more abstract concepts regarding how knowledge is formalized through logic in Python. Discover fundamental algorithms that are used for solving typical problems in computer science, along with some simple logic.
Extending-Python-Files-Errors-and-Graphs
Learn how to make your programs more relevant and usable in the IT world. Look at file operations, error handling and building graphs.
Getting-started-with-Python-Structures
Discover the most important data types in Python, including lists, dictionaries, tuples, and sets. Learn how to store and retrieve data effectively, and use advanced data structures to store complex data.
Interpreting-the-credit-card-defaulter-dataset
Explore data related to credit card defaulters to identify customer personas. Discover patterns in the data and interpret how each feature impacts the target variabl
Introduction-to-Data-Analytics-with-pandas-and-NumPy
Learn to use NumPy to perform statistics and speed up matrix computations as well as visualize data by constructing, modifying, and interpreting histograms and scatter plots. Discover how to generate and interpret statistical models using pandas and statsmodels and solve real-world problems using data analytics techniques.
Introduction-to-Python-Math-Strings-Conditionals-and-Loops
Dive into Python by getting an understanding of the core elements, keywords and syntax. Start writing Python programs by assigning variables, applying functions and combining math operations.
Investigating-Company-Bankruptcy
Investigate the reasons behind bankruptcy and attempt to identify early warning signs. Perform exploratory data analytics using pandas profiling and apply missing value treatments and oversampling
Making-Things-Interactive-with-Bokeh
Use Bokeh to create insightful web-based visualizations that can be extended into beautiful, interactive visualizations. Easily integrate visualizations into your web page.
Model-Evaluation
Learn and practice alternative evaluation techniques for models on which more standard accuracy methods are not feasible
Neighborhood-Approaches-and-DBSCAN
This course teaches you how to implement DBSCAN from scratch, describes the various DBSCAN attributes and helps you to evaluate the impact of neighborhood size. This course will help you identify the best suited algorithm from K-Means, hierarchical clustering, and DBSCAN to solve your problem
Performing-Classification-Tasks-with-Python
Implement logistic regression to classify data into specific groups. Learn to use the K-nearest neighbors algorithm, decision trees and artificial neural networks.
Regularization-for-Neural-Networks-in-Keras
Learn and practice several regularization techniques (including dropout regulation and hyperparameter-tuning) to improve model accuracy
Sequential-Modeling-with-Recurrent-Neural-Networks
Learn the concepts and applications of RNNs (specifically, Long Short-Term Method networks) and implement these architectures to build sequential models to predict results
Software-Development-with-Python
Learn how to troubleshoot issues in Python applications and explain why testing in software development is important. Also write test scenarios in Python to validate code and create a Python package that can be published to PyPI.
SQL-for-Data-Preparation
This module covers how to assemble multiple tables into a dataset using SQL queries. It also introduces how to transform and clean data using SQL functions.
Summarizing-and-Implementing-Different-Plots-with-Python
Apply all the concepts that you have learned throughout this learning path. Use Matplotlib, Seaborn, Geoplotlib, and Bokeh to create visualizations for a range of different datasets.
Transfer-Learning-with-Pre-Trained-Networks
Discover the theory behind transfer learning, how it works and the purpose it serves, and utilize pre-trained networks for image classification in practice
Understanding-the-Standard-Library
Learn about all the useful modules that the standard library has to offer.