In this 1-hour long guided project, you will learn how to use the "What-If" Tool (WIT) in the context of training and testing machine learning prediction models. In particular, you will learn a) how to set up a machine learning application in Python by using interactive Python notebook(s) on Google's Colab(oratory) environment, a.k.a. "zero configuration" environment, b) import and prepare the data, c) train and test classifiers as prediction models, d) analyze the behavior of the trained prediction models by using WIT for specific data points (individual basis), e) moving on to the analysis of the behavior of the trained prediction models by using WIT global basis, i.e., all test data considered. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

In this 2-hour project-based course, you will be able to : - Understand the Segmentation Dataset and you will write a custom dataset class for Image-mask dataset. Additionally, you will apply segmentation augmentation to augment images as well as its masks. For image-mask augmentation you will use albumentation library. You will plot the image-Mask pair. - Load a pretrained state of the art convolutional neural network for segmentation problem(for e.g, Unet) using segmentation model pytorch library. - Create train function and evaluator function which will helpful to write training loop. Moreover, you will use training loop to train the model.

In this 1 hour long project based course, you will learn to save, load and restore models with Keras. In Keras, we can save just the model weights, or we can save weights along with the entire model architecture. We can also export the models to TensorFlow's Saved Mode format which is very useful when serving a model in production, and we can load models from the Saved Model format back in Keras as well. In order to be successful in this project, you should be familiar with python programming, and basics of neural networks. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

In this short, 1 hour long guided project, we will use a Convolutional Neural Network - the popular VGG16 model, and we will visualize various filters from different layers of the CNN. We will do this by using gradient ascent to visualize images that maximally activate specific filters from different layers of the model. We will be using TensorFlow as our machine learning framework. The project uses the Google Colab environment which is a fantastic tool for creating and running Jupyter Notebooks in the cloud, and Colab even provides free GPUs for your notebooks. You will need prior programming experience in Python. This is a practical, hands on guided project for learners who already have theoretical understanding of Neural Networks, Convolutional Neural Networks, and optimization algorithms like gradient descent but want to understand how to use the TensorFlow to visualize various filters of a CNN. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

What is a certification? How is it different than a certificate or credential? This mini-course will answer these questions and provide learners direction on how to prepare for a certification exam from CertNexus or an other certification vendor. It includes tips and tricks to succeed in your journey towards certification, as well as step by step instructions how to schedule and take your exam, whether in person or online. In addition we will provide next steps after your certification, including posting your badge to social posts and your organization. Candidates with industry recognized certifications can earn up to 25% more than candidates without a certification. Learn how to successfully prepare for, pass, and share your certification.

Marketing data often requires categorization or labeling. In today’s age, marketing data can also be very big, or larger than what humans can reasonably tackle. In this course, students learn how to use supervised deep learning to train algorithms to tackle text classification tasks. Students walk through a conceptual overview of supervised machine learning and dive into real-world datasets through instructor-led tutorials in Python. The course concludes with a major project. This course can be taken for academic credit as part of CU Boulder’s Master of Science in Data Science (MS-DS) degree offered on the Coursera platform. The MS-DS is an interdisciplinary degree that brings together faculty from CU Boulder’s departments of Applied Mathematics, Computer Science, Information Science, and others. With performance-based admissions and no application process, the MS-DS is ideal for individuals with a broad range of undergraduate education and/or professional experience in computer science, information science, mathematics, and statistics. Learn more about the MS-DS program at https://www.coursera.org/degrees/master-of-science-data-science-boulder.

In this course, you’ll be learning various supervised ML algorithms and prediction tasks applied to different data. You’ll learn when to use which model and why, and how to improve the model performances. We will cover models such as linear and logistic regression, KNN, Decision trees and ensembling methods such as Random Forest and Boosting, kernel methods such as SVM. Prior coding or scripting knowledge is required. We will be utilizing Python extensively throughout the course. In this course, you will need to have a solid foundation in Python or sufficient previous experience coding with other programming languages to pick up Python quickly. We will be learning how to use data science libraries like NumPy, pandas, matplotlib, statsmodels, and sklearn. The course is designed for programmers beginning to work with those libraries. Prior experience with those libraries would be helpful but not necessary. College-level math skills, including Calculus and Linear Algebra, are required. Our hope for this course is that the math will be understandable but not intimidating. This course can be taken for academic credit as part of CU Boulder’s Master of Science in Data Science (MS-DS) degree offered on the Coursera platform. The MS-DS is an interdisciplinary degree that brings together faculty from CU Boulder’s departments of Applied Mathematics, Computer Science, Information Science, and others. With performance-based admissions and no application process, the MS-DS is ideal for individuals with a broad range of undergraduate education and/or professional experience in computer science, information science, mathematics, and statistics. Learn more about the MS-DS program at https://www.coursera.org/degrees/master-of-science-data-science-boulder.

In this hands-on project, we will train a Naive Bayes classifier to predict sentiment from thousands of Twitter tweets. This project could be practically used by any company with social media presence to automatically predict customer's sentiment (i.e.: whether their customers are happy or not). The process could be done automatically without having humans manually review thousands of tweets and customer reviews. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

This course will provide you a foundational understanding of machine learning models (logistic regression, multilayer perceptrons, convolutional neural networks, natural language processing, etc.) as well as demonstrate how these models can solve complex problems in a variety of industries, from medical diagnostics to image recognition to text prediction. In addition, we have designed practice exercises that will give you hands-on experience implementing these data science models on data sets. These practice exercises will teach you how to implement machine learning algorithms with PyTorch, open source libraries used by leading tech companies in the machine learning field (e.g., Google, NVIDIA, CocaCola, eBay, Snapchat, Uber and many more).

Please note: You will need an AWS account to complete this course. Your AWS account will be charged as per your usage. Please make sure that you are able to access Sagemaker within your AWS account. If your AWS account is new, you may need to ask AWS support for access to certain resources. You should be familiar with python programming, and AWS before starting this hands on project. We use a Sagemaker P type instance in this project, and if you don't have access to this instance type, please contact AWS support and request access. In this 2-hour long project-based course, you will learn how to train and deploy an object detector using Amazon Sagemaker. Sagemaker provides a number of machine learning algorithms ready to be used for solving a number of tasks. We will use the SSD Object Detection algorithm from Sagemaker to create, train and deploy a model that will be able to localize faces of dogs and cats from the popular IIIT-Oxford Pets Dataset. Since this is a practical, project-based course, we will not dive in the theory behind deep learning based SSD or Object Detection, but will focus purely on training and deploying a model with Sagemaker. You will also need to have some experience with Amazon Web Services (AWS). Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.