![I have a linear regression neural network which uses BERT encoding as input features. The model is always predicting the mean value. Any suggestion what can I do to overcome this problem? : I have a linear regression neural network which uses BERT encoding as input features. The model is always predicting the mean value. Any suggestion what can I do to overcome this problem? :](https://i.redd.it/jmjjmc6vv2c51.png)
I have a linear regression neural network which uses BERT encoding as input features. The model is always predicting the mean value. Any suggestion what can I do to overcome this problem? :
![Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets | Nature Communications Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets | Nature Communications](https://media.springernature.com/lw685/springer-static/image/art%3A10.1038%2Fs41467-020-18037-z/MediaObjects/41467_2020_18037_Fig1_HTML.png)
Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets | Nature Communications
![Regression-based neural networks: Predicting Average Daily Rates for Hotels | by Michael Grogan | Towards Data Science Regression-based neural networks: Predicting Average Daily Rates for Hotels | by Michael Grogan | Towards Data Science](https://miro.medium.com/v2/resize:fit:623/0*7-KjMeBfGT_XdHqa.png)