This is the code repository for Hands-On Machine Learning with Scikit-Learn and TensorFlow 2.0 [Video], published by Packt. It contains all the supporting project files necessary to work through the video course from start to finish.
Have you been looking for a course that teaches you effective machine learning in scikit-learn and TensorFlow 2.0? Or have you always wanted an efficient and skilled working knowledge of how to solve problems that can't be explicitly programmed through the latest machine learning techniques?
If you're familiar with pandas and NumPy, this course will give you up-to-date and detailed knowledge of all practical machine learning methods, which you can use to tackle most tasks that cannot easily be explicitly programmed; you'll also be able to use algorithms that learn and make predictions or decisions based on data.
The theory will be underpinned with plenty of practical examples, and code example walk-throughs in Jupyter notebooks. The course aims to make you highly efficient at constructing algorithms and models that perform with the highest possible accuracy based on the success output or hypothesis you've defined for a given task.
By the end of this course, you will be able to comfortably solve an array of industry-based machine learning problems by training, optimizing, and deploying models into production. Being able to do this effectively will allow you to create successful prediction and decisions for the task in hand (for example, creating an algorithm to read a labeled dataset of handwritten digits).
- Fundamentals of machine learning (and introducing the benefits of scikit-learn)
- Practical implementation with comprehensive examples of canonical machine learning, and supervised and unsupervised machine learning in scikit-learn
- How to identify a problem, select the right model, and optimize it to get the best desired outcome: insights into data
- TensorFlow 2.0 for deep learning with neural networks
- Deep learning and image-classification examples, and time series predictive model examples
- Reinforcement learning, and how to implement various types with examples
- Effectively use scikit-learn and TensorFlow in your production system, including framing a task in each task example
For successful completion of this course, students will require the computer systems with at least the following:
• Prior programming knowledge of Python
• Familiarity with pandas and NumPy concepts
For an optimal experience with hands-on labs and other practical activities, we recommend the following configuration:
• Windows 10
• OS: Microsoft Windows 10/8/7/Vista/2003/XP (incl.64-bit), macOS 10.8.3 or higher, GNOME or KDE desktop
• Processor: Dual core processor
• Memory: 2 GB RAM minimum, 4 GB RAM recommended
• Storage: 1.5 GB hard disk space + at least 1 GB for caches
• Optional: GPU: NVIDIA® GPU card with CUDA® Compute Capability 3.5 or higher.