From tech startups to global giants, organizations constantly look to incorporate trending technologies for their business expansion. Artificial Intelligence (AI) and Machine Learning (ML) are two such advanced technologies that hold the potential to present diverse cutting-edge solutions for businesses. At present, the AI-ML industry is growing at a rapid rate and provides ample development scope for organizations to bring the necessary transformation. As per Gartner, around 37 percent of all organizations surveyed are leveraging some form of AI in their business and it is predicted that about 80 percent of modern technologies will be based on AI and ML by 2022. Over the last few years, there have been several breakthroughs in artificial intelligence and machine learning.

A deep learning model--a form of artificial intelligence (AI)--was more accurate than the current clinical standard at predicting a person's 12-year risk of developing lung cancer. The model's predictions are based on chest radiograph images (CXRs) and basic demographic data (age, sex, and current smoking status) commonly available in electronic health records (EHRs). The findings are published in Annals of Internal Medicine. Lung cancer screening with chest computed tomography (CT) scans can prevent lung cancer death. However, Medicare's current standard to determine who is eligible for lung cancer screening CT misses most lung cancers. Furthermore, lung cancer screening participation is poor, with an estimated less than 5 percent of screening-eligible persons being screened.

With the training of deep learning models, how can we deploy the trained model as a web application? By leveraging on the functionality of Flask, we can establish a strong foundation for a full-stack application, explore new frontiers for a more extensive and feature-rich website. It enables the user to exercise full control over serving the web pages and internal data flow. We shall approach the following problem statements and explore the use of transfer learning and flask web application for deep learning projects. Instead of building a CNN model from scratch, let's address the problem statements by building upon the transfer learning idea as discussed in my earlier post:

This paper describes problems in AI research and how the SP System may help to solve them. Most of the problems are described by leading researchers in AI in interviews with science writer Martin Ford, and reported by him in his book Architects of Intelligence. These problems, each with potential solutions via SP, are: how to overcome the divide between symbolic and non-symbolic kinds of knowledge and processing; eliminating large and unexpected errors in recognition; the challenge of unsupervised learning; the problem of generalisation, with under- and over-generalisation; learning from a single exposure or experience; the problem of transfer learning; how to create learning that is fast, economical in demands for data and computer resources; the problems of transparency in results and processing; problems in the processing of natural language; problems in the development of probabilistic reasoning; the problem of catastrophic forgetting; how to achieve generality across several aspects of AI. The SP System provides a relatively promising foundation for the development of artificial general intelligence.

Efficiency and ease of use are essential for practical applications of camera based eye/gaze-tracking. Gaze tracking involves estimating where a person is looking on a screen based on face images from a computer-facing camera. In this paper we investigate two complementary forms of efficiency in gaze tracking: 1. The computational efficiency of the system which is dominated by the inference speed of a CNN predicting gaze-vectors; 2. The usability efficiency which is determined by the tediousness of the mandatory calibration of the gaze-vector to a computer screen. To do so, we evaluate the computational speed/accuracy trade-off for the CNN and the calibration effort/accuracy trade-off for screen calibration. For the CNN, we evaluate the full face, two-eyes, and single eye input. For screen calibration, we measure the number of calibration points needed and evaluate three types of calibration: 1. pure geometry, 2. pure machine learning, and 3. hybrid geometric regression. Results suggest that a single eye input and geometric regression calibration achieve the best trade-off.

Medical image datasets are usually imbalanced, due to the high costs of obtaining the data and time-consuming annotations. Training deep neural network models on such datasets to accurately classify the medical condition does not yield desired results and often over-fits the data on majority class samples. In order to address this issue, data augmentation is often performed on training data by position augmentation techniques such as scaling, cropping, flipping, padding, rotation, translation, affine transformation, and color augmentation techniques such as brightness, contrast, saturation, and hue to increase the dataset sizes. These augmentation techniques are not guaranteed to be advantageous in domains with limited data, especially medical image data, and could lead to further overfitting. In this work, we performed data augmentation on the Chest X-rays dataset through generative modeling (deep convolutional generative adversarial network) which creates artificial instances retaining similar characteristics to the original data and evaluation of the model resulted in Fr\'echet Distance of Inception (FID) score of 1.289.

The effects of adding pitch and voice quality features such as jitter and shimmer to a state-of-the-art CNN model for Automatic Speech Recognition are studied in this work. Pitch features have been previously used for improving classical HMM and DNN baselines, while jitter and shimmer parameters have proven to be useful for tasks like speaker or emotion recognition. Up to our knowledge, this is the first work combining such pitch and voice quality features with modern convolutional architectures, showing improvements up to 2% absolute WER points, for the publicly available Spanish Common Voice dataset. Particularly, our work combines these features with mel-frequency spectral coefficients (MFSCs) to train a convolutional architecture with Gated Linear Units (Conv GLUs). Such models have shown to yield small word error rates, while being very suitable for parallel processing for online streaming recognition use cases. We have added pitch and voice quality functionality to Facebook's wav2letter speech recognition framework, and we provide with such code and recipes to the community, to carry on with further experiments. Besides, to the best of our knowledge, our Spanish Common Voice recipe is the first public Spanish recipe for wav2letter.

Open-set recognition and adversarial defense study two key aspects of deep learning that are vital for real-world deployment. The objective of open-set recognition is to identify samples from open-set classes during testing, while adversarial defense aims to defend the network against images with imperceptible adversarial perturbations. In this paper, we show that open-set recognition systems are vulnerable to adversarial attacks. Furthermore, we show that adversarial defense mechanisms trained on known classes do not generalize well to open-set samples. Motivated by this observation, we emphasize the need of an Open-Set Adversarial Defense (OSAD) mechanism. This paper proposes an Open-Set Defense Network (OSDN) as a solution to the OSAD problem. The proposed network uses an encoder with feature-denoising layers coupled with a classifier to learn a noise-free latent feature representation. Two techniques are employed to obtain an informative latent feature space with the objective of improving open-set performance. First, a decoder is used to ensure that clean images can be reconstructed from the obtained latent features. Then, self-supervision is used to ensure that the latent features are informative enough to carry out an auxiliary task. We introduce a testing protocol to evaluate OSAD performance and show the effectiveness of the proposed method in multiple object classification datasets. The implementation code of the proposed method is available at: https://github.com/rshaojimmy/ECCV2020-OSAD.

Convolutional Neural Networks (CNNs) constitute a class of Deep Learning models which have been used in the recent past to resolve many problems in computer vision, in particular optical flow estimation. Measuring displacement and strain fields can be regarded as a particular case of this problem. However, it seems that CNNs have never been used so far to perform such measurements. This work is aimed at implementing a CNN able to retrieve displacement and strain fields from pairs of reference and deformed images of a flat speckled surface, as Digital Image Correlation (DIC) does. This paper explains how a CNN called StrainNet can be developed to reach this goal, and how specific ground truth datasets are elaborated to train this CNN. The main result is that StrainNet successfully performs such measurements, and that it achieves competing results in terms of metrological performance and computing time. The conclusion is that CNNs like StrainNet offer a viable alternative to DIC, especially for real-time applications.

Drafting in Magic: the Gathering is a sub-game of a larger trading card game, where several players progressively build decks by picking cards from a common pool. Drafting poses an interesting problem for game-playing and AI research due to its large search space, mechanical complexity, multiplayer nature, and hidden information. Despite this, drafting remains understudied in part due to a lack of high-quality, public datasets. To rectify this problem, we present a dataset of over 100,000 simulated, anonymized human drafts collected from Draftsim.com. Additionally, we propose four diverse strategies for drafting agents, including a primitive heuristic agent, an expert-tuned complex heuristic agent, a Naive Bayes agent, and a deep neural network agent. We benchmark their ability to emulate human drafting, and show that the deep neural network agent outperforms all other agents, while Naive Bayes and expert-tuned agents outperform simple heuristics. We analyze the accuracy of AI agents across the timeline of a draft, for different cards, and in terms of approximating subtle inconsistencies of human behavior, and describe unique strengths and weaknesses for each agent. This work helps to identify next steps in the creation of humanlike drafting agents, and can serve as a set of useful benchmarks for the next generation of drafting bots.