Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
binary_network [2018/09/13 10:56]
admin
binary_network [2018/11/04 13:10] (current)
admin
Line 82: Line 82:
  
 In all brevity, we represent the terms of a text as propositional variables. From these, we capture categories using simple propositional formulae, such as: if "​rash"​ and "​reaction"​ and "​penicillin"​ then Allergy. The Tsetlin Machine learns these formulae from a labelled text, utilizing conjunctive clauses to represent the particular facets of each category. Indeed, even the absence of terms (negated features) can be used for categorization purposes. Our empirical results are quite conclusive. The Tsetlin Machine either performs on par with or outperforms all of the evaluated methods on both the 20 Newsgroups and IMDb datasets, as well as on a non-public clinical dataset. On average, the Tsetlin Machine delivers the best recall and precision scores across the datasets. The GPU implementation of the Tsetlin Machine is further 8 times faster than the GPU implementation of the neural network. In all brevity, we represent the terms of a text as propositional variables. From these, we capture categories using simple propositional formulae, such as: if "​rash"​ and "​reaction"​ and "​penicillin"​ then Allergy. The Tsetlin Machine learns these formulae from a labelled text, utilizing conjunctive clauses to represent the particular facets of each category. Indeed, even the absence of terms (negated features) can be used for categorization purposes. Our empirical results are quite conclusive. The Tsetlin Machine either performs on par with or outperforms all of the evaluated methods on both the 20 Newsgroups and IMDb datasets, as well as on a non-public clinical dataset. On average, the Tsetlin Machine delivers the best recall and precision scores across the datasets. The GPU implementation of the Tsetlin Machine is further 8 times faster than the GPU implementation of the neural network.
 +
 +https://​arxiv.org/​pdf/​1809.09244.pdf No Multiplication?​ No Floating Point? No Problem!
 +Training Networks for Efficient Inference
 +
 +we train deep networks that emit only a
 +predefined, static number of discretized values. Despite reducing the number of
 +values that can be emitted from 2
 +32 to only 32, there is little to no degradation in
 +network performance across a variety of tasks. Compared to existing approaches
 +for discretization,​ our approach is both conceptually and programmatically simple
 +and has no stochastic component. Second, we provide a method to constrain the
 +network’s weights to a small number of unique values (typically 100-1000) by
 +employing a periodic adaptive clustering step during training.
 +
 +https://​arxiv.org/​abs/​1810.03538v1 Combinatorial Attacks on Binarized Neural Networks
 +
 +The discrete, non-differentiable nature of BNNs, which distinguishes them from their full-precision counterparts,​ poses a challenge to gradient-based attacks. In this work, we study the problem of attacking a BNN through the lens of combinatorial and integer optimization. ​
 +
 +https://​arxiv.org/​pdf/​1803.07125v2.pdf Local Binary Pattern Networks