What is Google TensorFlow?
According to Guru99, Google TensorFlow is an open-source end-to-end platform for creating Machine Learning applications. It is a symbolic math library that uses dataflow and differentiable programming to perform various tasks focused on the training and inference of deep neural networks. It allows developers to create machine learning applications using various tools, libraries, and community resources.
What is the history of TensorFlow?
According to Guru99, a couple of years ago, deep learning started to outperform all other machine learning algorithms when giving a massive amount of data. Google saw it could use these deep neural networks to improve its services:
- Gmail
- Photo
- Google search engine
They build a framework called Tensorflow to let researchers and developers work together on an AI model. Once developed and scaled, it allows lots of people to use it.
It was first made public in late 2015, while the first stable version appeared in 2017. It is open source under the Apache Open-Source license. You can use it, modify it, and redistribute the modified version for a fee without paying anything to Google.
How does TensorFlow work?
According to Guru99, TensorFlow enables you to build dataflow graphs and structures to define how data moves through a graph by taking inputs as a multi-dimensional array called Tensor. It allows you to construct a flowchart of operations that can be performed on these inputs, which goes at one end and comes at the other end as output.
Why is it called TensorFlow?
According to Guru99, It is called Tensorflow because it takes input as a multi-dimensional array, also known as tensors. You can construct a sort of flowchart of operations (called a Graph) that you want to perform on that input. The input goes in at one end, and then it flows through this system of multiple operations and comes out the other end as output.
Therefore, it is called TensorFlow because the tensor goes in it flows through a list of operations, and then it comes out the other side.
What is the Scalable Deep Learning with TensorFlow and Apache Spark course about?
This course starts with the basics of the tf.keras API including defining model architectures, optimizers, and saving/loading models. You then implement more advanced concepts such as callbacks, regularization, TensorBoard, and activation functions.
After training your models, you will integrate the MLflow tracking API to reproduce and version your experiments. You will also apply model interpretability libraries such as LIME and SHAP to understand how the network generates predictions. You will also learn about various Convolutional Neural Networks (CNNs) architectures and use them as a basis for transfer learning to reduce model training time.
Substantial class time is spent on scaling your deep learning applications, from distributed inference with pandas UDFs to distributed hyperparameter search with Hyperopt to distributed model training with Horovod. This course is taught fully in Python.
Course Duration:
Two days
Objectives:
Upon completion of the course, students should be able to:
- Build deep learning models using Keras/TensorFlow
- Scale the following:
- Model inference with pandas UDFs & pandas function API
- Hyperparameter tuning with HyperOpt
- Training of distributed TensorFlow models with Horovod
- Track, version, and reproduce experiments using MLflow
- Apply model interpretability libraries to understand & visualize model predictions
- Use CNNs (convolutional neural networks) and perform transfer learning & data augmentation to improve model performance
- Deploy deep learning models
Target Audience:
- Data scientist
- Machine learning engineer
Prerequisites:
- Intermediate experience with Python/pandas
- Familiarity with machine learning concepts
- Experience with PySpark
Additional Notes:
- The appropriate, web-based programming environment will be provided to students
- This class is taught in Python only
Topics:
- Intro to Neural Networks with Keras
- MLflow
- Convolutional Neural Networks
- Deep Learning Pipelines
- Horovod
Conclusion:
Google’s TensorFlow is currently the most famous and sought-after deep learning library because of its high accessibility. Google aims to provide its users with the best AI experience which it achieves with TensorFlow.
If you want to learn more about this deep learning framework then this course is ideal for you.
To enroll, contact P2L today!