A must for deep learning
August 17, 2018

A must for deep learning

Kevin Perkins | TrustRadius Reviewer
Score 8 out of 10
Vetted Review
Verified User

Overall Satisfaction with TensorFlow

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.

Pros

  • Visualizing learning
  • Ease of use
  • Good documentation

Cons

  • Simplify distributed learning examples in the Github repo
  • Provide more tutorials on distributed training
  • TensorFlow LSTMs decreased timeseries forecasting error by 50% when compared to a simple baseline.
  • Timeseries anomaly detection reports 20% fewer false positives when compared to a baseline.
Tensorflow has a more broad community of support.
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.

Comments

More Reviews of TensorFlow

  1. Home
  2. Machine Learning Tools
  3. TensorFlow Reviews
  4. User Review of TensorFlow