Inspired by the success of self attention mechanism and Transformer architecture in sequence transduction and image generation applications, we propose novel self attention-based architectures to improve the performance of adversarial latent codebased schemes in text generation. Adversarial latent code-based text generation has recently gained a lot of attention due to its promising results. In this paper, we take a step to fortify the architectures used in these setups, specifically AAE and ARAE. We benchmark two latent code-based methods (AAE and ARAE) designed based on adversarial setups. In our experiments, the Google sentence compression dataset is utilized to compare our method with these methods using various objective and subjective measures. The experiments demonstrate the proposed (self) attention-based models outperform the state-of-the-art in adversarial code-based text generation. Text generation is of particular interest in many natural language processing (NLP) applications such as dialogue systems, machine translation, image captioning and text summarization. Recent deep learning-based approaches to this problem can be categorized into three classes: auto-regressive or maximum likelihood estimation (MLE)-based, generative adversarial network (GAN)-based and reinforcement learning (RL)-based approaches. RNNs compactly represent the samples history in the form of recurrent states.

Person-Job Fit is the process of matching the right talent for the right job by identifying talent competencies that are required for the job. While many qualitative efforts have been made in related fields, it still lacks of quantitative ways of measuring talent competencies as well as the job's talent requirements. To this end, in this paper, we propose a novel end-to-end data-driven model based on Convolutional Neural Network (CNN), namely Person-Job Fit Neural Network (PJFNN), for matching a talent qualification to the requirements of a job. To be specific, PJFNN is a bipartite neural network which can effectively learn the joint representation of Person-Job fitness from historical job applications. In particular, due to the design of a hierarchical representation structure, PJFNN can not only estimate whether a candidate fits a job, but also identify which specific requirement items in the job posting are satisfied by the candidate by measuring the distances between corresponding latent representations. Finally, the extensive experiments on a large-scale real-world dataset clearly validate the performance of PJFNN in terms of Person-Job Fit prediction. Also, we provide effective data visualization to show some job and talent benchmark insights obtained by PJFNN.

Binarized Neural Networks (BNNs) have recently attracted significant interest due to their computational efficiency. Concurrently, it has been shown that neural networks may be overly sensitive to "attacks" - tiny adversarial changes in the input - which may be detrimental to their use in safety-critical domains. Designing attack algorithms that effectively fool trained models is a key step towards learning robust 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. We propose a Mixed Integer Linear Programming (MILP) formulation of the problem. While exact and flexible, the MILP quickly becomes intractable as the network and perturbation space grow. To address this issue, we propose IProp, a decomposition-based algorithm that solves a sequence of much smaller MILP problems. Experimentally, we evaluate both proposed methods against the standard gradient-based attack (FGSM) on MNIST and Fashion-MNIST, and show that IProp performs favorably compared to FGSM, while scaling beyond the limits of the MILP.

This paper proposes a two-stage scoring approach to help lenders decide their fund allocations in the peer-to-peer (P2P) lending market. The existing scoring approaches focus on only either probability of default (PD) prediction, known as credit scoring, or profitability prediction, known as profit scoring, to identify the best loans for investment. Credit scoring fails to deliver the main need of lenders on how much profit they may obtain through their investment. On the other hand, profit scoring can satisfy that need by predicting the investment profitability. However, profit scoring completely ignores the class imbalance problem where most of the past loans are non-default. Consequently, ignorance of the class imbalance problem significantly affects the accuracy of profitability prediction. Our proposed two-stage scoring approach is an integration of credit scoring and profit scoring to address the above challenges. More specifically, stage 1 is designed as credit scoring to identify non-default loans while the imbalanced nature of loan status is considered in PD prediction. The loans identified as non-default are then moved to stage 2 for prediction of profitability, measured by internal rate of return. Wide and deep learning is used to build the predictive models in both stages to achieve both memorization and generalization. Extensive numerical studies are conducted based on real-world data to verify the effectiveness of the proposed approach. The numerical studies indicate our two-stage scoring approach outperforms the existing credit scoring and profit scoring approaches.

One form of characterizing the expressiveness of a piecewise linear neural network is by the number of linear regions, or pieces, of the function modeled. We have observed substantial progress in this topic through lower and upper bounds on the maximum number of linear regions and a counting procedure. However, these bounds only account for the dimensions of the network and the exact counting may take a prohibitive amount of time, therefore making it infeasible to benchmark the expressiveness of networks. In addition, we present a tighter upper bound that leverages network coefficients. We test both on trained networks. The algorithm for probabilistic lower bounds is several orders of magnitude faster than exact counting and the values reach similar orders of magnitude, hence making our approach a viable method to compare the expressiveness of such networks. The refined upper bound is particularly stronger on networks with narrow layers. Neural networks with piecewise linear activations have become increasingly more common along the past decade, in particular since Nair & Hinton (2010) and Glorot et al. (2011). The simplest and most commonly used among such forms of activation is the Rectifier Linear Unit (ReLU), which outputs the maximum between 0 and its input argument (Hahnloser et al., 2000; LeCun et al., 2015). In the functions modeled by these networks, we can associate each part of the domain in which the network corresponds to an affine function with a particular set of units having positive outputs.

This past April a new video of Barack Obama surfaced on the Internet. Against a backdrop that included both the American and presidential flags, it looked like many of his previous speeches. Wearing a crisp white shirt and dark suit, Obama faced the camera and punctuated his words with outstretched hands: "President Trump is a total and complete dipshit." Without cracking a smile, he continued. "Now, you see, I would never say these things. The view shifted to a split screen, revealing the actor Jordan Peele. Obama hadn't said anything--it was a real recording of an Obama address blended with Peele's impersonation. Side by side, the message continued as Peele, like a digital ventriloquist, put more words in the former president's mouth. In this era of fake news, the video was a public service announcement produced by BuzzFeed News, showcasing an application of new artificial-intelligence (AI) technology that could do for audio and video what Photoshop has done for digital images: ...

It seems as if not a week goes by in which the artificial intelligence concepts of deep learning and neural networks make it into media headlines, either due to an exciting new use case or in an opinion piece speculating whether such rapid advances in AI will eventually replace the majority of human labor. Deep learning has improved speech recognition, genomic sequencing, and visual objection recognition, among many other areas. The availability of exceptionally powerful computer systems at a reasonable cost, combined with the influx of large swathes of data that define the so-called Age of Big Data and the talents of data scientists, have together provided the foundation for the accelerated growth and use of deep learning and neural networks. Companies are now beginning to adopt AI frameworks and libraries, such as MxNet, which is a deep learning framework that gives users the ability to train deep learning models using a variety of languages. There are also dedicated AI platforms aimed at supporting data scientists in deep learning modeling and training which professionals can integrate into their workflows.

It's a great time to get started doing deep learning with Kaggle Kernels! Recently I had the chance to give my first conference talk, at PyOhio in Columbus. I spoke about getting into deep learning, and I used Kaggle Kernels to demo some material from the first lesson of the fast.ai The next day I came across a Medium article called "Learn deep learning with GPU enabled kaggle kernels and fastai MOOC", and I was excited to see more people recognizing the capabilities of this platform. So I thought, if we're going to make it easy for people to get started with deep learning on Kaggle Kernels, why not make the whole fast.ai

Picterra combines deep learning with human expertise to help you extract structured insights from Earth observation imagery. Our AI platform is designed to help you process a large volume of aerial or satellite images, detect objects and trends, and monitor change over any area or period of interest, enabling you to unlock key insights, all from your desk with just a few clicks. AI that works for you. We provide a powerful all-in-one AI feature-extraction, classification, and change detection solution. This makes your work easier by streamlining your geospatial analytic processes and producing higher quality results.