Decision Machines: An Extension of Decision Trees
- URL: http://arxiv.org/abs/2101.11347v5
- Date: Sun, 2 Jun 2024 06:55:33 GMT
- Title: Decision Machines: An Extension of Decision Trees
- Authors: Jinxiong Zhang,
- Abstract summary: We draw the dependencies between prediction and binary tests in decision trees.
We provide a connection between decision trees and error-correcting output codes.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Here is a compact representation of binary decision trees. We can explicitly draw the dependencies between prediction and binary tests in decision trees and construct a procedure to guide the input instance from the root to its exit leaf. And we provided a connection between decision trees and error-correcting output codes. Then we built a bridge from tree-based models to attention mechanisms.
Related papers
- Terminating Differentiable Tree Experts [77.2443883991608]
We propose a neuro-symbolic Differentiable Tree Machine that learns tree operations using a combination of transformers and Representation Products.
We first remove a series of different transformer layers that are used in every step by introducing a mixture of experts.
We additionally propose a new termination algorithm to provide the model the power to choose how many steps to make automatically.
arXiv Detail & Related papers (2024-07-02T08:45:38Z) - An Algorithmic Framework for Constructing Multiple Decision Trees by
Evaluating Their Combination Performance Throughout the Construction Process [1.8749305679160366]
Predictions using a combination of decision trees are known to be effective in machine learning.
We propose a new algorithmic framework that constructs decision trees simultaneously and evaluates their combination performance.
arXiv Detail & Related papers (2024-02-09T14:58:07Z) - Learning a Decision Tree Algorithm with Transformers [80.49817544396379]
We introduce MetaTree, which trains a transformer-based model on filtered outputs from classical algorithms to produce strong decision trees for classification.
We then train MetaTree to produce the trees that achieve strong generalization performance.
arXiv Detail & Related papers (2024-02-06T07:40:53Z) - Greedy Algorithm for Inference of Decision Trees from Decision Rule
Systems [0.0]
Decision trees and decision rule systems play important roles as attributes, knowledge representation tools, and algorithms.
In this paper, we consider the inverse transformation problem, which is not so simple.
Instead of constructing an entire decision tree, our study focuses on a greedy time algorithm that simulates the operation of a decision tree on a given attribute.
arXiv Detail & Related papers (2024-01-08T09:28:55Z) - TreeDQN: Learning to minimize Branch-and-Bound tree [78.52895577861327]
Branch-and-Bound is a convenient approach to solving optimization tasks in the form of Mixed Linear Programs.
The efficiency of the solver depends on the branchning used to select a variable for splitting.
We propose a reinforcement learning method that can efficiently learn the branching.
arXiv Detail & Related papers (2023-06-09T14:01:26Z) - Construction of Decision Trees and Acyclic Decision Graphs from Decision
Rule Systems [0.0]
We study the complexity of constructing decision trees and acyclic decision graphs representing decision trees from decision rule systems.
We discuss the possibility of not building the entire decision tree, but describing the computation path in this tree for the given input.
arXiv Detail & Related papers (2023-05-02T18:40:48Z) - Structure-Unified M-Tree Coding Solver for MathWord Problem [57.825176412485504]
In previous work, models designed by taking into account the properties of the binary tree structure of mathematical expressions at the output side have achieved better performance.
In this paper, we propose the Structure-Unified M-Tree Coding Coding (S-UMCr), which applies a tree with any M branches (M-tree) to unify the output structures.
Experimental results on the widely used MAWPS and Math23K datasets have demonstrated that SUMC-r not only outperforms several state-of-the-art models but also performs much better under low-resource conditions.
arXiv Detail & Related papers (2022-10-22T12:20:36Z) - METGEN: A Module-Based Entailment Tree Generation Framework for Answer
Explanation [59.33241627273023]
We propose METGEN, a Module-based Entailment Tree GEN framework that has multiple modules and a reasoning controller.
Given a question, METGEN can iteratively generate the entailment tree by conducting single-step entailment with separate modules and selecting the reasoning flow with the controller.
Experiment results show that METGEN can outperform previous state-of-the-art models with only 9% of the parameters.
arXiv Detail & Related papers (2022-05-05T12:06:02Z) - Yet Another Representation of Binary Decision Trees: A Mathematical Demonstration [0.0]
A decision tree looks like a simple computational graph without cycles.
From the numerical perspective, we express decision trees in the language of computational graph.
arXiv Detail & Related papers (2021-01-18T13:50:14Z) - Rectified Decision Trees: Exploring the Landscape of Interpretable and
Effective Machine Learning [66.01622034708319]
We propose a knowledge distillation based decision trees extension, dubbed rectified decision trees (ReDT)
We extend the splitting criteria and the ending condition of the standard decision trees, which allows training with soft labels.
We then train the ReDT based on the soft label distilled from a well-trained teacher model through a novel jackknife-based method.
arXiv Detail & Related papers (2020-08-21T10:45:25Z) - dtControl: Decision Tree Learning Algorithms for Controller
Representation [0.0]
Decision trees can be used to represent provably-correct controllers concisely.
We present dtControl, an easily synthesised tool for representing memoryless controllers as decision trees.
arXiv Detail & Related papers (2020-02-12T17:13:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.