Course Overview
TOPThe abundance of data and affordable cloud scale has led to an explosion of interest in Deep Learning. Google has released an excellent library called Tensorflow to open-source, allowing state-of-the-art machine learning done at scale, complete with GPU-based acceleration. Working with Tensorflow is a hands-on course that explores algorithms, machine learning, and data mining concepts, and how TensorFlow implements them, working in a hands-on manner. This “skills-centric” course is about 50% hands-on lab and 50% lecture, integrating practical hands-on labs designed to reinforce fundamental skills, concepts and best practices introduced throughout the course.
Scheduled Classes
TOPWhat You'll Learn
TOPThis “skills-centric” course combines extensive practical exercises designed to reinforce fundamental skills, concepts and best practices taught throughout the course. Throughout the course, led by our expert team, students will explore:
- Core Deep Learning and Machine Learning math essentials
- TensorFlow Overview and Basics.
- TensorFlow Operations
- Neural Networks With TensorFlow
- Deep Learning With TensorFlow
Outline
TOP- Machine Learning & Deep Learning Overview
- This is summary of ML/DL Concepts (from the class – Machine Learning & Deep Learning Fundamentals)
- Mathematical Concepts
- ML Overview
- DL Overview
- Tensorflow – Overview & Basics
- Tensorflow – What is it? History & Background
- Use cases & Key Applications
- Machine Learning & Deep Learning Basics
- Environment, Configuration Settings & Installation
- Tensorflow Primitives
- Declaring Tensors
- Declaring Placeholders and Variables
- Working with Matrices
- Declaring Operations
- Operations in Computational Graph
- Nested Operations
- Multiple Layers
- Implementing Loss Functions
- Implementing Back Propagation
- Machine Learning With Tensorflow
- Linear Regression Review
- Linear Regression Using TensorFlow
- Support Vector Machines (SVM) Review
- SVM using TensorFlow
- Nearest Neighbor Method Review
- Nearest Neighbor Method using TensorFlow
- Neural Networks With Tensorflow
- Neural Networks Review
- Optimization and Operational Gates
- Working with Activation Functions
- Implementing One-Layer Neural Network
- Implementing Different Layers
- Implementing Multilayer Neural Networks
- Deep Neural Networks With Tensorflow
- Models and Overview
- Single Hidden Layer
- Multiple Hidden Layer
- Convolutional Neural Network Overview & Implementation
- CNN Architecture
- Recurrent Neural Network Overview & Implementation
- RNN Architecture
- Tensorflow: Additional Topics
- Tensorflow Extensions
- Scikit Flow
- TFLearn
- TF-Slim
- TensorLayer
- Keras
- Unit Testing
- Taking your implementation to production
- Other Misc Topics
Prerequisites
TOPStudents should have attended or have incoming skills equivalent to those in this course:
- Strong foundational mathematics in Linear Algebra and Probability; Matrix Transformation, Regressions, Standard Deviation, Statistics, Classification, etc.
- Basic knowledge of machine learning and deep learning algorithms
- Strong basic Python Skills
Attending students should have incoming skills equivalent to those in the course(s0 listed below or should have attended the course(s) as a pre-requisite:
- Machine Learning Essentials with Python
Who Should Attend
TOPThis in an intermediate-level course is geared for experienced developers or others (with prior Python experience) intending to start using and working with TensorFlow.
