Critical success factors behind a modern analytics landscape lies from the fact that it is not restricted to technical excellence but comes from answering the trickier "why" questions. This includes understanding deep learning models behind business problems; trusting data model predictions and explaining outcomes in a simple yet comprehensive language. Of late, many of the data scientists are more interested to sharpen their skills and unearth interesting nuggets buried in data than engaging themselves to this softer cause. Though this may sound natural with a narrow focus on data and the tools required to explore it, understanding the critical'why' is more mainstream to reach out to more users across the value chain. To understand the nuances of a Data Strategy, let us understand it from a consulting team's point of view who is assisting a large MNC to develop its data strategy.

With the rise of autonomous vehicles, smart video surveillance, facial detection and various people counting applications, fast and accurate object detection systems are rising in demand. These systems involve not only recognizing and classifying every object in an image, but localizing each one by drawing the appropriate bounding box around it. This makes object detection a significantly harder task than its traditional computer vision predecessor, image classification.

Erudtion Inc. provides training and consulting in Emerging technologies like Big Data, Artificial Intelligence, Deep Learning, AI, Blockchain, App development and AI/ML/App deployment through Kubernetes

Machine learning-based personalization has gained traction over the years due to volume in the amount of data across sources and the velocity at which consumers and organizations generate new data. Traditional ways of personalization focused on deriving business rules using techniques like segmentation, which often did not address a customer uniquely. Recent progress in specialized hardware (read GPUs and cloud computing) and a burgeoning ML and DL toolkits enable us to develop 1:1 customer personalization which scales. Recommender systems are beneficial to both service providers and users. They reduce transaction costs of finding and selecting items in an online shopping environment and improves customer experience.

Welcome (or welcome back!) to the AI for social good series! In the second part, of this two-part series of articles, we will look at how Artificial intelligence (AI) coupled with the power of open-source tools and techniques like deep learning can help us further the quest for finding extra-terrestrial intelligence! In the first part of this two-part series, we formulated our key objective and motivation behind doing this project. Briefly, we were looking at different radio-telescope signals simulated from SETI (Search for Extra-terrestrial Intelligence) Institute data. We leveraged techniques to process, analyze and visualize radio signals as spectrograms, which are basically visual representations of the raw signal.

Generating high quality uncertainty estimates for sequential regression, particularly deep recurrent networks, remains a challenging and open problem. Existing approaches often make restrictive assumptions (such as stationarity) yet still perform poorly in practice, particularly in presence of real world non-stationary signals and drift. This paper describes a flexible method that can generate symmetric and asymmetric uncertainty estimates, makes no assumptions about stationarity, and outperforms competitive baselines on both drift and non drift scenarios. This work helps make sequential regression more effective and practical for use in real-world applications, and is a powerful new addition to the modeling toolbox for sequential uncertainty quantification in general.

Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the non-robust yet useful features. This motivates us to preserve both robust and non-robust features and separate them with disentangled representation learning. Our proposed Adversarial Asymmetric Training (AAT) algorithm can reliably disentangle robust and non-robust representations without additional supervision on robustness. Empirical results show our method does not only successfully preserve accuracy by combining two representations, but also achieve much better disentanglement than previous work.

Generating an image from a provided descriptive text is quite a challenging task because of the difficulty in incorporating perceptual information (object shapes, colors, and their interactions) along with providing high relevancy related to the provided text. Current methods first generate an initial low-resolution image, which typically has irregular object shapes, colors, and interaction between objects. This initial image is then improved by conditioning on the text. However, these methods mainly address the problem of using text representation efficiently in the refinement of the initially generated image, while the success of this refinement process depends heavily on the quality of the initially generated image, as pointed out in the DM-GAN paper. Hence, we propose a method to provide good initialized images by incorporating perceptual understanding in the discriminator module. We improve the perceptual information at the first stage itself, which results in significant improvement in the final generated image. In this paper, we have applied our approach to the novel StackGAN architecture. We then show that the perceptual information included in the initial image is improved while modeling image distribution at multiple stages. Finally, we generated realistic multi-colored images conditioned by text. These images have good quality along with containing improved basic perceptual information. More importantly, the proposed method can be integrated into the pipeline of other state-of-the-art text-based-image-generation models to generate initial low-resolution images. We also worked on improving the refinement process in StackGAN by augmenting the third stage of the generator-discriminator pair in the StackGAN architecture. Our experimental analysis and comparison with the state-of-the-art on a large but sparse dataset MS COCO further validate the usefulness of our proposed approach.

Explainability is one of the key elements for building trust in AI systems. Among numerous attempts to make AI explainable, quantifying the effect of explanations remains a challenge in conducting human-AI collaborative tasks. Aside from the ability to predict the overall behavior of AI, in many applications, users need to understand an AI agent's competency in different aspects of the task domain. In this paper, we evaluate the impact of explanations on the user's mental model of AI agent competency within the task of visual question answering (VQA). We quantify users' understanding of competency, based on the correlation between the actual system performance and user rankings. We introduce an explainable VQA system that uses spatial and object features and is powered by the BERT language model. Each group of users sees only one kind of explanation to rank the competencies of the VQA model. The proposed model is evaluated through between-subject experiments to probe explanations' impact on the user's perception of competency. The comparison between two VQA models shows BERT based explanations and the use of object features improve the user's prediction of the model's competencies.

Deep learning bears promise for drug discovery, including advanced image analysis, prediction of molecular structure and function, and automated generation of innovative chemical entities with bespoke properties. Despite the growing number of successful prospective applications, the underlying mathematical models often remain elusive to interpretation by the human mind. There is a demand for 'explainable' deep learning methods to address the need for a new narrative of the machine language of the molecular sciences. This review summarizes the most prominent algorithmic concepts of explainable artificial intelligence, and dares a forecast of the future opportunities, potential applications, and remaining challenges.