On Symbolically Encoding the Behavior of Random Forests

• URL: http://arxiv.org/abs/2007.01493v1
• Date: Fri, 3 Jul 2020 04:21:47 GMT
• Title: On Symbolically Encoding the Behavior of Random Forests
• Abstract summary: Recent work has shown that the input-output behavior of some machine learning systems can be captured symbolically. We address systems with discrete inputs and outputs, including ones with discretized continuous variables. We show some key distinctions with encodings for satisfiability, and propose an encoding that is sound and complete for the given task.
• Score: 21.79165388471151
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work has shown that the input-output behavior of some machine learning systems can be captured symbolically using Boolean expressions or tractable Boolean circuits, which facilitates reasoning about the behavior of these systems. While most of the focus has been on systems with Boolean inputs and outputs, we address systems with discrete inputs and outputs, including ones with discretized continuous variables as in systems based on decision trees. We also focus on the suitability of encodings for computing prime implicants, which have recently played a central role in explaining the decisions of machine learning systems. We show some key distinctions with encodings for satisfiability, and propose an encoding that is sound and complete for the given task.

Related papers

• CLAIRE: Compressed Latent Autoencoder for Industrial Representation and Evaluation -- A Deep Learning Framework for Smart Manufacturing [51.56484100374058]
  CLAIRE is a hybrid end-to-end learning framework that integrates unsupervised deep representation learning with supervised classification for intelligent quality control in smart manufacturing systems.<n>It employs an optimized deep autoencoder to transform raw input into a compact latent space, effectively capturing the intrinsic data structure while suppressing irrelevant or noisy features.<n>The proposed framework highlights the potential of integrating explainable AI with feature-aware regularization for robust fault detection.
  arXiv  Detail & Related papers  (2026-03-06T15:11:58Z)
• On Improving Neurosymbolic Learning by Exploiting the Representation Space [54.16389421332958]
  We study the problem of learning neural classifiers in a neurosymbolic setting where the hidden gold labels of input instances must satisfy a logical formula.<n>One challenge is that the space of label combinations can grow exponentially, making learning difficult.<n>We propose a technique that prunes this space by exploiting the intuition that instances with similar latent representations are likely to share the same label.
  arXiv  Detail & Related papers  (2026-02-08T13:56:47Z)
• Evaluating perturbation robustnessof generative systems that use COBOL code inputs [1.3327839779221817]
  Systems incorporating large language models (LLMs) as a component are known to be sensitive (i.e., non-robust) to minor input variations.<n>Here, we present a framework to evaluate robustness of systems using code as input.
  arXiv  Detail & Related papers  (2025-11-23T15:16:08Z)
• BlackBoxToBlueprint: Extracting Interpretable Logic from Legacy Systems using Reinforcement Learning and Counterfactual Analysis [0.0]
  This paper proposes a novel pipeline to automatically extract interpretable decision logic from legacy systems treated as black boxes.<n>The approach uses a Reinforcement Learning (RL) agent to explore the input space and identify critical decision boundaries by rewarding actions that cause meaningful changes in the system's output.<n>Decision trees are then trained on these clusters to extract human-readable rules that approximate the system's decision logic near the identified boundaries.
  arXiv  Detail & Related papers  (2025-06-30T18:36:54Z)
• BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language? [88.29075896295357]
  We first investigate whether current retrieval systems can comprehend the Boolean logic implied in language. Through extensive experimental results, we draw the conclusion that current dense retrieval systems do not fully understand Boolean logic in language. We propose a contrastive continual training method that serves as a strong baseline for the research community.
  arXiv  Detail & Related papers  (2024-11-19T05:19:53Z)
• Gradient-based Fuzzy System Optimisation via Automatic Differentiation -- FuzzyR as a Use Case [14.211148966253438]
  We focus on automatic differentiation--crucial to neural network learning--with a view to free fuzzy system designers from intricate derivative computations. We present a use case in FuzzyR which demonstrates how current fuzzy inference system implementations can be adjusted to leverage powerful features of automatic differentiation tools sets.
  arXiv  Detail & Related papers  (2024-03-18T23:18:16Z)
• The Predictive Forward-Forward Algorithm [79.07468367923619]
  We propose the predictive forward-forward (PFF) algorithm for conducting credit assignment in neural systems. We design a novel, dynamic recurrent neural system that learns a directed generative circuit jointly and simultaneously with a representation circuit. PFF efficiently learns to propagate learning signals and updates synapses with forward passes only.
  arXiv  Detail & Related papers  (2023-01-04T05:34:48Z)
• Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions [69.40242990198]
  Neuro-Symbolic (NeSy) integration combines symbolic reasoning with Neural Networks (NNs) for tasks requiring perception and reasoning. Most NeSy systems rely on continuous relaxation of logical knowledge, and no discrete decisions are made within the model pipeline. We propose a NeSy system that learns NeSy-functions, i.e., the composition of a (set of) perception functions which map continuous data to discrete symbols, and a symbolic function over the set of symbols.
  arXiv  Detail & Related papers  (2022-08-24T14:06:55Z)
• Hierarchical Sketch Induction for Paraphrase Generation [79.87892048285819]
  We introduce Hierarchical Refinement Quantized Variational Autoencoders (HRQ-VAE), a method for learning decompositions of dense encodings. We use HRQ-VAE to encode the syntactic form of an input sentence as a path through the hierarchy, allowing us to more easily predict syntactic sketches at test time.
  arXiv  Detail & Related papers  (2022-03-07T15:28:36Z)
• Improving Compositionality of Neural Networks by Decoding Representations to Inputs [83.97012077202882]
  We bridge the benefits of traditional and deep learning programs by jointly training a generative model to constrain neural network activations to "decode" back to inputs. We demonstrate applications of decodable representations to out-of-distribution detection, adversarial examples, calibration, and fairness.
  arXiv  Detail & Related papers  (2021-06-01T20:07:16Z)
• Latent Programmer: Discrete Latent Codes for Program Synthesis [56.37993487589351]
  In many sequence learning tasks, such as program synthesis and document summarization, a key problem is searching over a large space of possible output sequences. We propose to learn representations of the outputs that are specifically meant for search: rich enough to specify the desired output but compact enough to make search more efficient. We introduce the emphLatent Programmer, a program synthesis method that first predicts a discrete latent code from input/output examples, and then generates the program in the target language.
  arXiv  Detail & Related papers  (2020-12-01T10:11:35Z)
• Learning event-driven switched linear systems [7.766921168069532]
  We propose an automata theoretic learning algorithm for the identification of black-box switched linear systems. Our algorithm first uses the oracle to obtain the node labels of the system run on a given input sequence of events, and then extends Angluin's (L*)-algorithm to determine the FA that accepts the language of the given FA.
  arXiv  Detail & Related papers  (2020-09-27T12:32:40Z)
• Explainable AI for Classification using Probabilistic Logic Inference [9.656846523452502]
  We present an explainable classification method. Our method works by first constructing a symbolic Knowledge Base from the training data, and then performing probabilistic inferences on such Knowledge Base with linear programming. It identifies decisive features that are responsible for a classification as explanations and produces results similar to the ones found by SHAP, a state of the artley Value based method.
  arXiv  Detail & Related papers  (2020-05-05T11:39:23Z)
• On The Reasons Behind Decisions [11.358487655918676]
  We define notions such as sufficient, necessary and complete reasons behind decisions. We show how these notions can be used to evaluate counterfactual statements. We present efficient algorithms for computing these notions.
  arXiv  Detail & Related papers  (2020-02-21T13:37:29Z)

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.