mlsanityData to 7 Oct 2026

Seeking Interpretability and Explainability in Binary Activated Neural Networks

arXiv 2209.03450 ↗First posted 7 Sep 2022cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

We study the use of binary activated neural networks as interpretable and explainable predictors in the context of regression tasks on tabular data; more specifically, we provide guarantees on their expressiveness, present an approach based on the efficient computation of SHAP values for quantifying the relative importance of the features, hidden neurons and even weights. As the model's simplicity is instrumental in achieving interpretability, we propose a greedy algorithm for building compact binary activated networks. This approach doesn't need to fix an architecture for the network in advance: it is built one layer at a time, one neuron at a time, leading to predictors that aren't needlessly complex for a given task.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 41 of its 75 references that are in the map. First posted on arXiv 7 Sep 2022.

Builds on

41 of 75 references.

References · 41

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  5. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  6. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  7. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  8. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  9. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  10. 2020What is the State of Neural Network Pruning?cited by 578
  11. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  12. 2016Error bounds for approximations with deep ReLU networkscited by 567
29 more
  1. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  2. 2019The State of Sparsity in Deep Neural Networkscited by 471
  3. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  4. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 283
  5. 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 279
  6. 2020Comparing Rewinding and Fine-tuning in Neural Network Pruningcited by 238
  7. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  8. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
  9. 2016Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architecturescited by 220
  10. 2016Trained Ternary Quantizationcited by 203
  11. 2016Ternary Weight Networkscited by 195
  12. 2020Binary Neural Networks: A Surveycited by 184
  13. 2018Optimal approximation of continuous functions by very deep ReLU networkscited by 165
  14. 2019Quantization Networkscited by 151
  15. 2015Compressing Neural Networks with the Hashing Trickcited by 150
  16. 2018Greedy Layerwise Learning Can Scale to ImageNetcited by 113
  17. 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95
  18. 2016Why Deep Neural Networks for Function Approximation?cited by 82
  19. 2017Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMMcited by 60
  20. 2017SPINE: SParse Interpretable Neural Embeddingscited by 55
  21. 2019Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networkscited by 38
  22. 2019Stabilizing the Lottery Ticket Hypothesiscited by 36
  23. 2020Training Binary Neural Networks using the Bayesian Learning Rulecited by 22
  24. 2020A Greedy Algorithm for Quantizing Neural Networkscited by 21
  25. 2021Chickenpox Cases in Hungary: a Benchmark Dataset for Spatiotemporal Signal Processing with Graph Neural Networkscited by 19
  26. 2017Layer-wise training of deep networks using kernel similaritycited by 15
  27. 2018On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networkscited by 11
  28. 2018The universal approximation power of finite-width deep ReLU networkscited by 11
  29. 2019Greedy Shallow Networks: An Approach for Constructing and Training Neural Networkscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Eventizing Traditionally Opaque Binary Neural Networks as 1-safe Petri net Modelscited by 0
  2. 2026Position: Explainable AI is Causality in Disguisecited by 0
  3. 2026A Composite Activation Function for Learning Stable Binary Representationscited by 0