We propose a novel three-layer neural network architecture with threshold activations for tabular data classification problems. The hidden layer units correspond to trainable neurons with arbitrary weights and biases and a step activation. These neurons are logically equivalent to threshold logic functions. The output layer neuron is also a threshold function that implements a conjunction of the hidden layer threshold functions. This neural network architecture can leverage state-of-the-art network training methods to achieve high prediction accuracy, and the network is designed so that minimal human understandable explanations can be readily derived from the model. Further, we employ a sparsity-promoting regularization approach to sparsify the threshold functions to simplify them, and to sparsify the output neuron so that it only depends on a small subset of hidden layer threshold functions. Experimental results show that our approach outperforms other state-of-the-art interpretable decision models in prediction accuracy.
more »
« less
Disjunctive Threshold Networks for Tabular Data Classification
While neural networks have been achieving increasingly significant excitement in solving classification tasks such as natural language processing, their lack of interpretability becomes a great challenge for neural networks to be deployed in certain high-stakes human-centered applications. To address this issue, we propose a new approach for generating interpretable predictions by inferring a simple three-layer neural network with threshold activations, so that it can benefit from effective neural network training algorithms and at the same time, produce human-understandable explanations for the results. In particular, the hidden layer neurons in the proposed model are trained with floating point weights and binary output activations. The output neuron is also trainable as a threshold logic function that implements a disjunctive operation, forming the logical-OR of the first-level threshold logic functions. This neural network can be trained using state-of-the-art training methods to achieve high prediction accuracy. An important feature of the proposed architecture is that only a simple greedy algorithm is required to provide an explanation with the prediction that is human-understandable. In comparison with other explainable decision models, our proposed approach achieves more accurate predictions on a broad set of tabular data classification datasets.
more »
« less
- Award ID(s):
- 1956339
- NSF-PAR ID:
- 10475629
- Editor(s):
- IEEE Open Journal of the Computer Society
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE Open Journal of the Computer Society
- Volume:
- 4
- ISSN:
- 2644-1268
- Page Range / eLocation ID:
- 185 to 194
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
While neural networks are used for classification tasks across domains, a long-standing open problem in machine learning is determining whether neural networks trained using standard procedures are consistent for classification, i.e., whether such models minimize the probability of misclassification for arbitrary data distributions. In this work, we identify and construct an explicit set of neural network classifiers that are consistent. Since effective neural networks in practice are typically both wide and deep, we analyze infinitely wide networks that are also infinitely deep. In particular, using the recent connection between infinitely wide neural networks and neural tangent kernels, we provide explicit activation functions that can be used to construct networks that achieve consistency. Interestingly, these activation functions are simple and easy to implement, yet differ from commonly used activations such as ReLU or sigmoid. More generally, we create a taxonomy of infinitely wide and deep networks and show that these models implement one of three well-known classifiers depending on the activation function used: 1) 1-nearest neighbor (model predictions are given by the label of the nearest training example); 2) majority vote (model predictions are given by the label of the class with the greatest representation in the training set); or 3) singular kernel classifiers (a set of classifiers containing those that achieve consistency). Our results highlight the benefit of using deep networks for classification tasks, in contrast to regression tasks, where excessive depth is harmful.more » « less
-
Multilayer neural networks set the current state of the art for many technical classification problems. But, these networks are still, essentially, black boxes in terms of analyzing them and predicting their performance. Here, we develop a statistical theory for the one-layer perceptron and show that it can predict performances of a surprisingly large variety of neural networks with different architectures. A general theory of classification with perceptrons is developed by generalizing an existing theory for analyzing reservoir computing models and connectionist models for symbolic reasoning known as vector symbolic architectures. Our statistical theory offers three formulas leveraging the signal statistics with increasing detail. The formulas are analytically intractable, but can be evaluated numerically. The description level that captures maximum details requires stochastic sampling methods. Depending on the network model, the simpler formulas already yield high prediction accuracy. The quality of the theory predictions is assessed in three experimental settings, a memorization task for echo state networks (ESNs) from reservoir computing literature, a collection of classification datasets for shallow randomly connected networks, and the ImageNet dataset for deep convolutional neural networks. We find that the second description level of the perceptron theory can predict the performance of types of ESNs, which could not be described previously. Furthermore, the theory can predict deep multilayer neural networks by being applied to their output layer. While other methods for prediction of neural networks performance commonly require to train an estimator model, the proposed theory requires only the first two moments of the distribution of the postsynaptic sums in the output neurons. Moreover, the perceptron theory compares favorably to other methods that do not rely on training an estimator model.more » « less
-
There is an increasing number of pre-trained deep neural network models. However, it is still unclear how to effectively use these models for a new task. Transfer learning, which aims to transfer knowledge from source tasks to a target task, is an effective solution to this problem. Fine-tuning is a popular transfer learning technique for deep neural networks where a few rounds of training are applied to the parameters of a pre-trained model to adapt them to a new task. Despite its popularity, in this paper we show that fine-tuning suffers from several drawbacks. We propose an adaptive fine-tuning approach, called AdaFilter, which selects only a part of the convolutional filters in the pre-trained model to optimize on a per-example basis. We use a recurrent gated network to selectively fine-tune convolutional filters based on the activations of the previous layer. We experiment with 7 public image classification datasets and the results show that AdaFilter can reduce the average classification error of the standard fine-tuning by 2.54%.more » « less
-
We prove the first superpolynomial lower bounds for learning one-layer neural networks with respect to the Gaussian distribution using gradient descent. We show that any classifier trained using gradient descent with respect to square-loss will fail to achieve small test error in polynomial time given access to samples labeled by a one-layer neural network. For classification, we give a stronger result, namely that any statistical query (SQ) algorithm (including gradient descent) will fail to achieve small test error in polynomial time. Prior work held only for gradient descent run with small batch sizes, required sharp activations, and applied to specific classes of queries. Our lower bounds hold for broad classes of activations including ReLU and sigmoid. The core of our result relies on a novel construction of a simple family of neural networks that are exactly orthogonal with respect to all spherically symmetric distributions.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/OJCS.2023.3282948
