Using TensorFlow for Intelligent Applications
TensorFlow is currently the most practical and accessible open-source machine learning tool for integrating intelligent features into our applications. Our organizations rely on petabytes of aggregated, structured data we’ve collected over the years. Even with good business intelligence practices, competitive position is increasingly defined by the ability to integrate an “intelligence layer” into the applications which ingest and utilize our data.
For software developers and data engineers ready to expand their silo and integrate intelligent services into applications, this TensoFlow course trains up engineering teams to build on domain expertise and design machine intelligence features using the popular TensorFlow library. TensorFlow delivers a myriad of deep learning best practices as part of its default configuration so complex machine learning just works out of the box.
TensorFlow democratizes deep learning for anyone with Python or C capability, but machine learning is not just another programming language. Our workshop allows you to learn from a live teacher, tie machine learning to value-driven use cases, and ask real-time questions in class.
Duration
2 days/16 hours of instructionPublic Classroom Pricing
$1750(USD)
GSA Price: $1640
Group Rate: $1650
Private Group Pricing
Have a group of 5 or more students? Request special pricing for private group training today.
Part 1: Overview of TensorFlow and TensorFlow libraries
- Using Python with TensorFlow
- Translating meaningful information into geometric spaces
- Training infrastructure
- Regressors
- Keras API
- Estimators and experiments
Part 2: Use cases for a machine learning service
- Deep learning implementation
- AI and macro insight opportunities
- Image processing use cases
- Predictive use cases
- Scoring datasets for machine learning
- Estimators
Part 3: Using and applying your model
- Defining the model
- Training the model
- Evaluating the model
- Prediction outputs
Part 4: Training your model
- Setting up the training cycle
- Training data
- Adjusting bias
- Weights
Part 5: Testing your model
- Testing overview
- Model values vs. output values
Part 6: Using TensorBoard to visualize model performance
- Loss curve
- Biases
- Examining graphs
- Learning rate decay
This course is for individuals with intermediate experience with Python and C. Any experience with TensorFlow is also beneficial. Additionally, although it is not mandatory, students who have completed the self-pacedApplied Statistics for Data Scientists eLearning course have found it very helpful when completing this course