What Are the Solutions to Underfitting?
- Increasing model complexity
- For an algorithm, add more high-order items to the regression model, improve the depth of the decision tree, or increase the number of hidden layers and hidden units of the neural network to increase model complexity.
- Discard the original algorithm and use a more complex algorithm or model. For example, use the neural network to replace the linear regression, and use the random forest to replace the decision tree.
- Adding more features to make input data more expressive
- Feature mining is very important. Specifically, features with strong expression capabilities can outperform a large number of features with weak expression capabilities.
- Feature quality is the focus.
- To explore features with strong expression capabilities, you must have an in-depth understanding of data and application scenarios, which depends on experience.
- Adjusting parameters and hyperparameters
- Neural network: learning rate, learning attenuation rate, number of hidden layers, number of units in a hidden layer, β1 and β2 parameters in the Adam optimization algorithm, and batch_size
- Other algorithms: number of trees in the random forest, number of clusters in k-means, and regularization parameter λ
- Adding training data (not recommended)
Underfitting is usually caused by weak model learning capabilities. Adding data cannot significantly increase the training effect.
- Reducing regularization constraints
Regularization aims to prevent model overfitting. If a model is underfitting instead of overfitting, reduce the regularization parameter λ or directly remove the regularization item.
Functional Consulting FAQs
- What Are the Format Requirements for Algorithms Imported from a Local Environment?
- What Are the Solutions to Underfitting?
- What Are the Precautions for Switching Training Jobs from the Old Version to the New Version?
- How Do I Obtain a Trained ModelArts Model?
- How Do I Set the Runtime Environment of the AI Engine Scikit_Learn 0.18.1?
- Must the Hyperparameters Optimized Using a TPE Algorithm Be Categorical?
- What Is TensorBoard Used for in Model Visualization Jobs?
- How Do I Obtain RANK_TABLE_FILE on ModelArts for Distributed Training?
- How Do I Obtain the CUDA and cuDNN Versions of a Custom Image?
- How Do I Obtain a MoXing Installation File?
- In a Multi-Node Training, the TensorFlow PS Node Functioning as a Server Will Be Continuously Suspended. How Does ModelArts Determine Whether the Training Is Complete? Which Node Is a Worker?
- How Do I Install MoXing for a Custom Image of a Training Job?
- An IAM User Cannot Select an Existing SFS Turbo File System When Using a Dedicated Resource Pool to Create a Training Job
Feedback
Was this page helpful?
Provide feedbackThank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.
For any further questions, feel free to contact us through the chatbot.
Chatbotmore