This guided project is for those who want to learn how to use Julia for linear regression and multiple linear regression. You will learn what linear regression is, how to build linear regression models in Julia and how to test the performance of your model. While you are watching me code, you will get a cloud desktop with all the required software pre-installed. This will allow you to code along with me. After all, we learn best with active, hands-on learning. Special Features: 1) Work with real-world stock market data. 2) Best practices and tips are provided. 3) You get a copy of the jupyter notebook that you create which acts as a handy reference guide. Please note that the version of Julia used is 1.0.4 Note: This project works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

By the end of this project, you will extract colors pixels as training dataset into a form where you can feed it to your Machine Learning Model using numpy arrays. In this project we will work with images, you will get introduced to computer vision basic concepts. Moreover, you will be able to properly handle arrays and preprocess your training dataset and label it. Extracting features and preparing data is a very crucial task as it influences your model. So you will start to learn the basics of handling the data into the format where it would be accepted by a Machine Learning algorithm as Training Dataset.

In this 1 hour long guided project, you will learn to create and train multi-task, multi-output models with Keras. You will learn to use Keras' functional API to create a multi output model which will be trained to learn two different labels given the same input example. The model will have one input but two outputs. A few of the shallow layers will be shared between the two outputs, you will also use a ResNet style skip connection in the model. If you are familiar with Keras, you have probably come across examples of models that are trained to perform multiple tasks. For example, an object detection model where a CNN is trained to find all class instances in the input images as well as give a regression output to localize the detected class instances in the input. Being able to use Keras' functional API is a first step towards building complex, multi-output models like object detection models. We will be using TensorFlow as our machine learning framework. The project uses the Google Colab environment. You will need prior programming experience in Python. You will also need prior experience with Keras. Consider this to be an intermediate level Keras project. 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 use Keras to write custom, more complex models than just plain sequential 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.

Developing insights about your organization, business, or research project depends on effective modeling and analysis of the data you collect. Building effective models requires understanding the different types of questions you can ask and how to map those questions to your data. Different modeling approaches can be chosen to detect interesting patterns in the data and identify hidden relationships. This course covers the types of questions you can ask of data and the various modeling approaches that you can apply. Topics covered include hypothesis testing, linear regression, nonlinear modeling, and machine learning. With this collection of tools at your disposal, as well as the techniques learned in the other courses in this specialization, you will be able to make key discoveries from your data for improving decision-making throughout your organization. In this specialization we assume familiarity with the R programming language. If you are not yet familiar with R, we suggest you first complete R Programming before returning to complete this course.

In this hands-on project, we will train a Bidirectional Neural Network and LSTM based deep learning model to detect fake news from a given news corpus. This project could be practically used by any media company to automatically predict whether the circulating news is fake or not. The process could be done automatically without having humans manually review thousands of news related articles. 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 course, you will develop your data science skills while solving real-world problems. You'll work through the data science process to and use unsupervised learning to explore data, engineer and select meaningful features, and solve complex supervised learning problems using tree-based models. You will also learn to apply hyperparameter tuning and cross-validation strategies to improve model performance. NOTE: This is the third and final course in the Data Science with Databricks for Data Analysts Coursera specialization. To be successful in this course we highly recommend taking the first two courses in that specialization prior to taking this course. These courses are: Apache Spark for Data Analysts and Data Science Fundamentals for Data Analysts.

This is a hands-on project on transfer learning for natural language processing with TensorFlow and TF Hub. By the time you complete this project, you will be able to use pre-trained NLP text embedding models from TensorFlow Hub, perform transfer learning to fine-tune models on real-world data, build and evaluate multiple models for text classification with TensorFlow, and visualize model performance metrics with Tensorboard. Prerequisites: In order to successfully complete this project, you should be competent in the Python programming language, be familiar with deep learning for Natural Language Processing (NLP), and have trained models with TensorFlow or and its Keras API. 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 1.5-hour long project-based course, you will learn how to apply image data augmentation in Keras. We are going to focus on using the ImageDataGenerator class from Keras’ image preprocessing package, and will take a look at a variety of options available in this class for data augmentation and data normalization. Since this is a practical, project-based course, you will need to prior experience with Python programming, convolutional neural networks, and Keras with a TensorFlow backend. Data augmentation is a technique used to create more examples, artificially, from an existing dataset. This is useful if your dataset is small and you want to increase the number of examples. Data augmentation can often solve over-fitting so that your model generalizes well after training. For images, a variety of augmentation can be applied to increase the number of examples. 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.

Business professionals in non-technical roles have a unique opportunity to lead or influence machine learning projects. If you have questions about machine learning and want to understand how to use it, without the technical jargon, this course is for you. Learn how to translate business problems into machine learning use cases and vet them for feasibility and impact. Find out how you can discover unexpected use cases, recognize the phases of an ML project and considerations within each, and gain confidence to propose a custom ML use case to your team or leadership or translate the requirements to a technical team.

In this 1.5 hour long project-based course, you will learn to create and train a Convolutional Neural Network (CNN) with an existing CNN model architecture, and its pre-trained weights. We will use the MobileNet model architecture along with its weights trained on the popular ImageNet dataset. By using a model with pre-trained weights, and then training just the last layers on a new dataset, we can drastically reduce the training time required to fit the model to the new data . The pre-trained model has already learned to recognize thousands on simple and complex image features, and we are using its output as the input to the last layers that we are training. In order to be successful in this project, you should be familiar with Python, Neural Networks, and CNNs. 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.