Search for: All records

Improving the performance and explanations of ML algorithms is a priority for adoption by humans in the real world. In critical domains such as healthcare, such technology has significant potential to reduce the burden on humans and considerably reduce manual assessments by providing quality assistance at scale. In today’s data-driven world, artificial intelligence (AI) systems are still experiencing issues with bias, explainability, and human-like reasoning and interpretability. Causal AI is the technique that can reason and make human-like choices making it possible to go beyond narrow Machine learning-based techniques and can be integrated into human decision-making. It also offers intrinsic explainability, new domain adaptability, bias free predictions, and works with datasets of all sizes. In this tutorial of type lecture style, we detail how a richer representation of causality in AI systems using a knowledge graph (KG) based approach is needed for intervention and counterfactual reasoning (Figure 1), how do we get to model-based and domain explainability, how causal representations helps in web and health care. 

Language understanding involves processing text with both the grammatical and 2 common-sense contexts of the text fragments. The text “I went to the grocery store 3 and brought home a car” requires both the grammatical context (syntactic) and 4 common-sense context (semantic) to capture the oddity in the sentence. Contex5 tualized text representations learned by Language Models (LMs) are expected to 6 capture a variety of syntactic and semantic contexts from large amounts of training 7 data corpora. Recent work such as ERNIE has shown that infusing the knowl8 edge contexts, where they are available in LMs, results in significant performance 9 gains on General Language Understanding (GLUE) benchmark tasks. However, 10 to our knowledge, no knowledge-aware model has attempted to infuse knowledge 11 through top-down semantics-driven syntactic processing (Eg: Common-sense to 12 Grammatical) and directly operated on the attention mechanism that LMs leverage 13 to learn the data context. We propose a learning framework Top-Down Language 14 Representation (TDLR) to infuse common-sense semantics into LMs. In our 15 implementation, we build on BERT for its rich syntactic knowledge and use the 16 knowledge graphs ConceptNet and WordNet to infuse semantic knowledge. 

In the ever-changing world of computer security and user authentication, the username/password standard is becoming increasingly outdated. Using the same username and password across multiple accounts and websites leaves a user open to vulnerabilities, and the need to remember multiple usernames and passwords feels very unnecessary in the current digital age. Authentication methods of the future need to be reliable and fast, while maintaining the ability to provide secure access. Augmenting traditional username-password standard with face biometric is proposed in the literature to enhance the user authentication. However, this technique still needs an extensive evaluation study to show how reliable and effective it will be under different settings. Local Binary Pattern (LBP) is a discrete yet powerful texture classification scheme, which works particularly well with image classification for facial recognition. The system proposed here strives to examine and test various LBP configurations to determine their image classification accuracy. The most favorable configurations of LBP should be examined as a potential way to augment the current username and password standard by increasing their security with facial biometrics. 

Deep learning methods have been very successful at radio frequency fingerprinting tasks, predicting the identity of transmitting devices with high accuracy. We study radio frequency fingerprinting deployments at resource-constrained edge devices. We use structured pruning to jointly train and sparsify neural networks tailored to edge hardware implementations. We compress convolutional layers by a 27.2× factor while incurring a negligible prediction accuracy decrease (less than 1%). We demonstrate the efficacy of our approach over multiple edge hardware platforms, including a Samsung Galaxy S10 phone and a Xilinx-ZCU104 FPGA. Our method yields significant inference speedups, 11.5× on the FPGA and 3× on the smartphone, as well as high efficiency: the FPGA processing time is 17× smaller than in a V100 GPU. To the best of our knowledge, we are the first to explore the possibility of compressing networks for radio frequency fingerprinting; as such, our experiments can be seen as a means of characterizing the informational capacity associated with this specific learning task. 

Methylation, which is one of the most prominent post-translational modifications on proteins, regulates many important cellular functions. Though several model-based methylation site predictors have been reported, all existing methods employ machine learning strategies, such as support vector machines and random forest, to predict sites of methylation based on a set of “hand-selected” features. As a consequence, the subsequent models may be biased toward one set of features. Moreover, due to the large number of features, model development can often be computationally expensive. In this paper, we propose an alternative approach based on deep learning to predict arginine methylation sites. Our model, which we termed DeepRMethylSite, is computationally less expensive than traditional feature-based methods while eliminating potential biases that can arise through features selection. Based on independent testing on our dataset, DeepRMethylSite achieved efficiency scores of 68%, 82% and 0.51 with respect to sensitivity (SN), specificity (SP) and Matthew's correlation coefficient (MCC), respectively. Importantly, in side-by-side comparisons with other state-of-the-art methylation site predictors, our method performs on par or better in all scoring metrics tested.