Can tensorflow be used for non-deep learning machine learning?

Can tensorflow be used for non-deep learning machine learning? Like logistic regression, xgboost, random forest etc.?

I just started listening to lesson #8 v1 on my commutes :slight_smile: Hope I will survive the TF :slight_smile: I listened about this today.

This seems to have been a nice initiative. Not sure where it went though? Maybe it got sucked into TF in a fashion similar to Keras?
https://curiosity.com/videos/ml-toolkit-tensorflow-dev-summit-2017-google-developers/

Yes, In a way. Tensorflow is for neural networks (I dont really use Tensorflow so Its possible it supports other algorithms). A single layer neural network is basically the same as logistic regression. @jeremy explains in lesson 6 or 7 of the ML course.

1 Like

I see there are few “non-deep learning” algorithms being implemented under tf.contrib : https://github.com/tensorflow/tensorflow/tree/r1.10/tensorflow/contrib

Yes, TensorFlow can be used for non-deep learning machine learning as well. Although TensorFlow is primarily known for its deep learning capabilities, it is a flexible and powerful platform that can be used for a wide range of machine learning tasks.

TensorFlow provides a variety of tools and APIs for building and training machine learning models, including linear regression, logistic regression, decision trees, and random forests. These algorithms are commonly used in non-deep learning machine learning tasks.

In addition, TensorFlow’s high-performance computing capabilities and its ability to scale to large datasets make it a popular choice for non-deep learning tasks that require processing large amounts of data.
Machine Learning Course in Pune

One example of non-deep learning tasks that can be performed using TensorFlow is anomaly detection. Anomaly detection is a process of identifying unusual patterns or events in data that do not conform to expected behavior. TensorFlow can be used to build machine learning models that can detect anomalies in data, such as fraudulent transactions or faulty equipment.

Another example is time series analysis. Time series analysis involves analyzing and predicting patterns in time series data. TensorFlow provides several tools and APIs for time series analysis, including ARIMA (Autoregressive Integrated Moving Average) models and LSTM (Long Short-Term Memory) networks.

In summary, while TensorFlow is best known for its deep learning capabilities, it is a versatile platform that can be used for a wide range of machine learning tasks, including non-deep learning tasks such as linear regression, decision trees, and anomaly detection.