Altran has released a new tool that uses artificial intelligence (AI) to help software engineers spot bugs during the coding process instead of at the end. Available on GitHub, Code Defect AI uses machine learning (ML) to analyze existing code, spot potential problems in new code, and suggest tests to diagnose and fix the errors. Walid Negm, group chief innovation officer at Altran, said that this new tool will help developers release quality code quickly. "The software release cycle needs algorithms that can help make strategic judgments, especially as code gets more complex," he said in a press release. Code Defect AI uses several ML techniques including random decision forests, support vector machines, multilayer perceptron (MLP) and logistic regression.

This post is part of "AI education", a series of posts that review and explore educational content on data science and machine learning. When it comes to software development education, I'm a classical type: I prefer books over video tutorials, and I like to manually write every single line of code instead of copy-pasting from sample files and Stack Exchange. My early experience with online artificial intelligence and machine learning courses had mostly left me disappointed. So, when Udemy gave me access to their online course "Machine Learning A-Z: Hands-On Python & R In Data Science," I was a bit skeptical. But after going through the course, I must say that the instructors, Kirill Eremenko and Hadelin de Ponteves, have done a great job to make machine learning, a fairly complicated topic, accessible to a wide audience.

Class imbalance is an inherent characteristic of multi-label data that hinders most multi-label learning methods. One efficient and flexible strategy to deal with this problem is to employ sampling techniques before training a multi-label learning model. Although existing multi-label sampling approaches alleviate the global imbalance of multi-label datasets, it is actually the imbalance level within the local neighbourhood of minority class examples that plays a key role in performance degradation. To address this issue, we propose a novel measure to assess the local label imbalance of multi-label datasets, as well as two multi-label sampling approaches based on the local label imbalance, namely MLSOL and MLUL. By considering all informative labels, MLSOL creates more diverse and better labeled synthetic instances for difficult examples, while MLUL eliminates instances that are harmful to their local region. Experimental results on 13 multi-label datasets demonstrate the effectiveness of the proposed measure and sampling approaches for a variety of evaluation metrics, particularly in the case of an ensemble of classifiers trained on repeated samples of the original data.

In this paper, the decades-old clustering method k-means is revisited. The original distortion minimization model of k-means is addressed by a pure stochastic minimization procedure. In each step of the iteration, one sample is tentatively reallocated from one cluster to another. It is moved to another cluster as long as the reallocation allows the sample to be closer to the new centroid. This optimization procedure converges faster to a better local minimum over k-means and many of its variants. This fundamental modification over the k-means loop leads to the redefinition of a family of k-means variants. Moreover, a new target function that minimizes the summation of pairwise distances within clusters is presented. We show that it could be solved under the same stochastic optimization procedure. This minimization procedure built upon two minimization models outperforms k-means and its variants considerably with different settings and on different datasets.

Attention architectures are widely used; they recently gained renewed popularity with Transformers yielding a streak of state of the art results. Yet, the geometrical implications of softmax-attention remain largely unexplored. In this work we highlight the limitations of constraining attention weights to the probability simplex and the resulting convex hull of value vectors. We show that Transformers are sequence length dependent biased towards token isolation at initialization and contrast Transformers to simple max- and sum-pooling - two strong baselines rarely reported. We propose to replace the softmax in self-attention with normalization, yielding a hyperparameter and data-bias robust, generally applicable architecture. We support our insights with empirical results from more than 25,000 trained models. All results and implementations are made available.

We propose a new estimator for the change point parameter in a dynamic high dimensional graphical model setting. We show that the proposed estimator retains sufficient adaptivity against plugin estimates of the edge structure of the underlying graphical models, in order to yield an $O(\psi^{-2})$ rate of convergence of the change point estimator in the integer scale. This rate is preserved while allowing high dimensionality as well as a diminishing jump size $\psi,$ provided $s\log^{3/2}(p\vee T)=o\big(\surd(Tl_T)\big).$ Here $s,p,T$ and $l_T$ represent a sparsity parameter, model dimension, sampling period and the separation of the change point from its parametric boundary, respectively. Moreover, since the rate of convergence is free of $s,p$ and logarithmic terms of $T,$ it allows the existence of a limiting distribution valid in the high dimensional setting, which is then derived. The method does not assume an underlying Gaussian distribution. Theoretical results are supported numerically with monte carlo simulations.

In this paper, we propose a new Semi-Nonnegative Matrix Factorization method for 2-dimensional (2D) data, named TS-NMF. It overcomes the drawback of existing methods that seriously damage the spatial information of the data by converting 2D data to vectors in a preprocessing step. In particular, projection matrices are sought under the guidance of building new data representations, such that the spatial information is retained and projections are enhanced by the goal of clustering, which helps construct optimal projection directions. Moreover, to exploit nonlinear structures of the data, manifold is constructed in the projected subspace, which is adaptively updated according to the projections and less afflicted with noise and outliers of the data and thus more representative in the projected space. Hence, seeking projections, building new data representations, and learning manifold are seamlessly integrated in a single model, which mutually enhance other and lead to a powerful data representation. Comprehensive experimental results verify the effectiveness of TS-NMF in comparison with several state-of-the-art algorithms, which suggests high potential of the proposed method for real world applications.

We introduce a graph clustering algorithm that generalizes $k$-means to graphs. Our method utilizes PageRank measures on graphs to quickly and robustly compute centrality of nodes in a given graph. Furthermore, we show how our method can be generalized to metric spaces and apply it to other domains such as point clouds and triangulated meshes.

Spatio-temporal sequence forecasting is one of the fundamental tasks in spatio-temporal data mining. It facilitates many real world applications such as precipitation nowcasting, citywide crowd flow prediction and air pollution forecasting. Recently, a few Seq2Seq based approaches have been proposed, but one of the drawbacks of Seq2Seq models is that, small errors can accumulate quickly along the generated sequence at the inference stage due to the different distributions of training and inference phase. That is because Seq2Seq models minimise single step errors only during training, however the entire sequence has to be generated during the inference phase which generates a discrepancy between training and inference. In this work, we propose a novel curriculum learning based strategy named Temporal Progressive Growing Sampling to effectively bridge the gap between training and inference for spatio-temporal sequence forecasting, by transforming the training process from a fully-supervised manner which utilises all available previous ground-truth values to a less-supervised manner which replaces some of the ground-truth context with generated predictions. To do that we sample the target sequence from midway outputs from intermediate models trained with bigger timescales through a carefully designed decaying strategy. Experimental results demonstrate that our proposed method better models long term dependencies and outperforms baseline approaches on two competitive datasets.

Intrusion detection is one of the primary mechanisms to provide computer networks with security. With an increase in attacks and growing dependence on various fields such as medicine, commercial, and engineering to give services over a network, securing networks have become a significant issue. The purpose of Intrusion Detection Systems (IDS) is to make models which can recognize regular communications from abnormal ones and take necessary actions. Among different methods in this field, Artificial Neural Networks (ANNs) have been widely used. However, ANN-based IDS, has two main disadvantages: 1- Low detection precision. 2- Weak detection stability. To overcome these issues, this paper proposes a new approach based on Deep Neural Network (DNN. The general mechanism of our model is as follows: first, some of the data in dataset is properly ranked, afterwards, dataset is normalized with Min-Max normalizer to fit in the limited domain. Then dimensionality reduction is applied to decrease the amount of both useless dimensions and computational cost. After the preprocessing part, Mean-Shift clustering algorithm is the used to create different subsets and reduce the complexity of dataset. Based on each subset, two models are trained by Support Vector Machine (SVM) and deep learning method. Between two models for each subset, the model with a higher accuracy is chosen. This idea is inspired from philosophy of divide and conquer. Hence, the DNN can learn each subset quickly and robustly. Finally, to reduce the error from the previous step, an ANN model is trained to gain and use the results in order to be able to predict the attacks. We can reach to 95.4 percent of accuracy. Possessing a simple structure and less number of tunable parameters, the proposed model still has a grand generalization with a high level of accuracy in compared to other methods such as SVM, Bayes network, and STL.