Guide MLP design and implementation for tabular data classification and regression.
npx skills add https://github.com/hung-phan/ml-skills --skill ann
Please help me install this Agent Skill. Skill: ann Source: https://github.com/hung-phan/ml-skills/tree/main/skills/ml-review/references/ml-architectures/ann Command: npx skills add https://github.com/hung-phan/ml-skills --skill ann
This Skill addresses the challenge of building feedforward neural networks for tabular data by providing a comprehensive guide on multi-layer perceptrons (MLPs), including their architecture, activation functions, weight initialization, and learning rate scheduling.
Train an MLP using the provided template and dataset 'tabular_data.csv'.
High-intent search queries and answers about installing and using this skill.
To build a multi-layer perceptron for tabular data classification, design a feedforward neural network architecture and configure activation functions, weight initialization, and learning rate scheduling using the provided PyTorch or Keras training templates.
For training neural networks on tabular data, you can use ReLU, GELU, SiLU/Swish, or Leaky ReLU activation functions. Each has specific pros and cons for gradient flow and convergence behavior in feedforward architectures.
Weight initialization significantly impacts multi-layer perceptron training convergence. Xavier/Glorot and He/Kaiming initialization methods help prevent vanishing or exploding gradients by scaling initial weights based on layer input and output dimensions.
Yes, you can use OneCycleLR and Warmup + Cosine Decay for learning rate scheduling in PyTorch. Both strategies are provided to optimize training efficiency for multi-layer perceptrons on tabular datasets.
Choose a multi-layer perceptron for tabular data regression when you need a feedforward neural network capable of capturing complex non-linear relationships. This Skill provides foundational knowledge for architecture design and implementation.
Yes, this Skill includes complete training templates for multi-layer perceptrons using both PyTorch and Keras frameworks, allowing you to implement and optimize models for tabular data classification and regression tasks.
Yeachan-HeoLoad, clean, and summarize tabular datasets with descriptive statistics.
Lord1EgyptLoad, run, and fine-tune pre-trained transformer models for NLP, vision, and audio tasks.
tachyon-beepRoute training problems to optimization specialists based on symptoms.
GuitarAlchemistClassify tabular data using random forests and gradient boosting.
