TensorFlow Information Reviews & Insights

TensorFlow is used as a development platform for deep learning algorithms, in particular for:
1. Recommendations: selecting the best templates to recommend to users via email in the various countries the company has a market in, over 100 languages supported,
2. User feedback classification: when users provide feedback, natural language processing algorithms implemented in TensorFlow and Keras are used to classify issues so that stakeholders can identify the major issues with a product/product release,
3. Learning-to-rank for search: there is some development on improving search results by switching to deep learning algorithms from a gradient boosting one, and TensorFlow provides that capability, and
4. Computer vision: some experimentation performed on object detection and image classification.

TensorFlow is great for most deep learning purposes. This is especially true in two domains:
1. Computer vision: image classification, object detection and image generation via generative adversarial networks
2. Natural language processing: text classification and generation.

The good community support often means that a lot of off-the-shelf models can be used to prove a concept or test an idea quickly. That, and Google's promotion of Colab means that ideas can be shared quite freely. Training, visualizing and debugging models is very easy in TensorFlow, compared to other platforms (especially the good old Caffe days).

In terms of productionizing, it's a bit of a mixed bag. In our case, most of our feature building is performed via Apache Spark. This means having to convert Parquet (columnar optimized) files to a TensorFlow friendly format i.e., protobufs. The lack of good JVM bindings mean that our projects end up being a mix of Python and Scala. This makes it hard to reuse some of the tooling and support we wrote in Scala. This is where MXNet shines better (though its Scala API could do with more work).

TensorFlow is the best deep learning library for visualization, training and tuning the model with a large dataset. We are using TensorFlow in the research and development department for the training of natural language, image processing and for the application of specific predictive models. It is also used by the production department to support and host the trained models at the application level.

TensorFlow is well-suited for complex model training with a large dataset using multiple GPU's and provides training time mode visualization for fast debugging of the architecture. If you are doing a proof of concept for new architecture then it would not be a good choice considering implementation complexity and development time.

Tensorflow (TF) is one of the Machine Learning (ML) libraries at LinkedIn. The necessary plumbing needed to deploy, maintain and monitor a TF project is under active development. It is currently used for building Wide and Deep Neural Networks, where training data is in the order of millions. However, in production, tree-based models or logistic regression are still popular.

We use TensorfFow to solve challenging machine learning problems at scale. TensorfFow fills in the gaps where other machine learning paradigms such as scikit learn fail. Tensorflow is used by several departments in our organization on many user facing business problems. Tensorflow provides an intuitive way to generate and train neural networks. There are also nice visualizations with TensorBoard.

TensorFlow is a must for deep learning. If deep learning is not necessary then other machine learning packages such as scikit-learn are a more appropriate choice. We have found that TensorFlow can be very useful in performing anomaly detection on time series data. TensorFlow provides easy aAPI for generating LSTM and CNN neural networks.