Predictive Modeling & Deep Learning
What you will learn
Build intelligent algorithms that can self-correct and self-heal. Discover methods to interpret real-time analysis of data to automate andincrease efficiency across all business domains, setting the stage for meaningful AI that moves from reactive to predictive. Sign up for free access today and sample 7,151 courses, 110+ Practice Labs, and 10+ live online bootcamps across 67 subjects.
Course | 1h 28m 28s
Explore deep learning and the implementation of deep learning-based frameworks for NLP and audio data analysis. Discover the architectures of recurrent neural network, the challenges associated with unsupervised learning, prominent statistical classification models, and the differences between generative classifiers and discriminative classifiers. The different types of generative models, the characteristics of the different classes of artificial neural networks, and the essential capabilities and variants of ResNet are also covered. We will also explore the roles of Encoders and Autoencoders in Deep learning implementations and work with PixelCNN.
Course | 41m 40s
Explore how to work with feature selection, general classes of feature selection algorithms, and predictive modeling best practices. Discover how to implement predictive models with scatter plots, boxplots, and crosstabs using Python.
Practice Lab | 8h
Perform DL programming tasks with Python, such as performing series expansion and calculus, and work with Tensorflow and scikit-image. Then, test your skills by answering assessment questions after loading a data set for hierarchical clustering and k-means clustering, and train a model using random forests and gradient boosting. This lab provides access to several tools commonly used in machine learning, including Microsoft Excel 2016, Visual Studio Code, Anaconda, Jupyter Notebook + JupyterHub, Pandas, NumPy, SiPy, Seaborn Library, and Spyder IDE.