Chart Classification Using Siamese CNN

In recovering information from the chart image, the first step should be chart type classification. Throughout history, many approaches have been used, and some of them achieve results better than others. The latest articles are using a Support Vector Machine (SVM) in combination with a Convolutional Neural Network (CNN), which achieve almost perfect results with the datasets of few thousand images per class. The datasets containing chart images are primarily synthetic and lack real-world examples. To overcome the problem of small datasets, to our knowledge, this is the first report of using Siamese CNN architecture for chart type classification. Multiple network architectures are tested, and the results of different dataset sizes are compared. The network verification is conducted using Few-shot learning (FSL). Many of described advantages of Siamese CNNs are shown in examples. In the end, we show that the Siamese CNN can work with one image per class, and a 100% average classification accuracy is achieved with 50 images per class, where the CNN achieves only average classification accuracy of 43% for the same dataset.

ProbNV: probabilistic verification of network control planes

ProbNV is a new framework for probabilistic network control plane verification that strikes a balance between generality and scalability. ProbNV is general enough to encode a wide range of features from the most common protocols (eBGP and OSPF) and yet scalable enough to handle challenging properties, such as probabilistic all-failures analysis of medium-sized networks with 100-200 devices. When there are a small, bounded number of failures, networks with up to 500 devices may be verified in seconds. ProbNV operates by translating raw CISCO configurations into a probabilistic and functional programming language designed for network verification. This language comes equipped with a novel type system that characterizes the sort of representation to be used for each data structure: concrete for the usual representation of values; symbolic for a BDD-based representation of sets of values; and multi-value for an MTBDD-based representation of values that depend upon symbolics. Careful use of these varying representations speeds execution of symbolic simulation of network models. The MTBDD-based representations are also used to calculate probabilistic properties of network models once symbolic simulation is complete. We implement the language and evaluate its performance on benchmarks constructed from real network topologies and synthesized routing policies.

Towards Scalable Complete Verification of Relu Neural Networks via Dependency-based Branching

We introduce an efficient method for the complete verification of ReLU-based feed-forward neural networks. The method implements branching on the ReLU states on the basis of a notion of dependency between the nodes. This results in dividing the original verification problem into a set of sub-problems whose MILP formulations require fewer integrality constraints. We evaluate the method on all of the ReLU-based fully connected networks from the first competition for neural network verification. The experimental results obtained show 145% performance gains over the present state-of-the-art in complete verification.

DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis

We propose a novel, complete algorithm for the verification and analysis of feed-forward, ReLU-based neural networks. The algorithm, based on symbolic interval propagation, introduces a new method for determining split-nodes which evaluates the indirect effect that splitting has on the relaxations of successor nodes. We combine this with a new efficient linear-programming encoding of the splitting constraints to further improve the algorithm’s performance. The resulting implementation, DeepSplit, achieved speedups of 1–2 orders of magnitude and 21-34% fewer timeouts when compared to the current SoA toolkits.

Efficient Neural Network Verification via Layer-based Semidefinite Relaxations and Linear Cuts

We introduce an efficient and tight layer-based semidefinite relaxation for verifying local robustness of neural networks. The improved tightness is the result of the combination between semidefinite relaxations and linear cuts. We obtain a computationally efficient method by decomposing the semidefinite formulation into layerwise constraints. By leveraging on chordal graph decompositions, we show that the formulation here presented is provably tighter than current approaches. Experiments on a set of benchmark networks show that the approach here proposed enables the verification of more instances compared to other relaxation methods. The results also demonstrate that the SDP relaxation here proposed is one order of magnitude faster than previous SDP methods.

Automated verification, assembly, and extension of GBM stem cell network model with knowledge from literature and data

Signaling network models are usually assembled from information in literature and expert knowledge or inferred from data. The goal of modeling is to gain mechanistic understanding of key signaling pathways and provide predictions on how perturbations affect large-scale processes such as disease progression. For glioblastoma multiforme (GBM), this task is critical, given the lack of effective treatments and pace of disease progression. Both manual and automated assembly of signaling networks from data or literature have drawbacks. Existing GBM networks, as well as networks assembled using state-of-the-art machine reading, fall short when judged by the quality and quantity of information, as well as certain attributes of the overall network structure. The contributions of this work are two-fold. First, we propose an automated methodology for verification of signaling networks. Next, we discuss automation of network assembly and extension that relies on methods and resources used for network verification, thus, implicitly including verification in these processes. In addition to these methods, we also present, and verify a comprehensive GBM network assembled with a hybrid of manual and automated methods. Finally, we demonstrate that, while an automated network assembly is fast, such networks still lack precision and realistic network topology.