Machine Learning Models play a vital part in Artificial Intelligence. In simple words, they are mathematical representations. In other words, they are the output we receive after training a process. What a machine learning model does is discovers the patterns in a training dataset. In other words, machine learning models map inputs to the outputs of the given dataset.

We saw excellent progress with enterprise acceptance of machine learning across a wide swath of industries and problem domains. In terms of pure research, I had a good time tracking the acceleration of progress in the area of machine learning. In this article, we'll take a tour of my top pick of papers that I found intriguing and useful. In my attempt to stay current with the field's research progress, the directions represented here are very promising. I hope you enjoy the results as much as I have. Overfitting & underfitting and stable training are important challenges in machine learning. Current approaches for these issues are mixup, SamplePairing, and BC learning. This paper states the hypothesis that mixing many images together can be more effective than just two.

Every time you search for something in Google, a whole mechanism functions behind the screen to bring about the results you are looking for. Similarly, many Google products are pegged to artificial intelligence, making it some of the few disruptive initiatives with the potential to revolutionize many industry verticals. The connection between Google and artificial intelligence goes way back to 2007. Google introduced people to its groundbreaking work, Android. As an open-source operating system for phones, Android stole the mobile industry for more than a decade now.

Taught by DeepMind researchers, this series was created in collaboration with University College London (UCL) to offer students a comprehensive introduction to modern reinforcement learning. Comprising 13 lectures, the series covers the fundamentals of reinforcement learning and planning in sequential decision problems, before progressing to more advanced topics and modern deep RL algorithms. It gives students a detailed understanding of various topics, including Markov Decision Processes, sample-based learning algorithms (e.g. It also explores more advanced topics like off-policy learning, multi-step updates and eligibility traces, as well as conceptual and practical considerations in implementing deep reinforcement learning algorithms such as rainbow DQN.

Researchers are calling into doubt the popular idea that deep-learning models are "black boxes" that reveal nothing about what goes on inside Load up the website This Person Does Not Exist and it'll show you a human face, near-perfect in its realism yet totally fake. Refresh and the neural network behind the site will generate another, and another, and another. The endless sequence of AI-crafted faces is produced by a generative adversarial network (GAN)--a type of AI that learns to produce realistic but fake examples of the data it is trained on. But such generated faces--which are starting to be used in CGI movies and ads--might not be as unique as they seem. In a paper titled This Person (Probably) Exists, researchers show that many faces produced by GANs bear a striking resemblance to actual people who appear in the training data.

Deep Instinct applies deep learning to cybersecurity--going beyond what machine learning can ... [ ] accomplish with a neural network designed to emulate the human brain and learn as it goes. Cyber attacks are not a new issue by any stretch of the imagination--but they are a rapidly growing threat. As the volume and types of technologies businesses and consumers use continues to expand, the attack surface--the configuration errors, vulnerabilities, human errors, or other weaknesses that increase the potential for a successful cyber attack--increases exponentially. To keep pace with the threat landscape, organizations need to rethink their approach to security. According to AVTest, there are more than 18,000 new malware and/or potentially unwanted applications identified every hour.

Abstract: More than 13% of U.S. adults suffer from hearing loss. Some causes include exposure to loud noises, physical head injuries, and presbycusis. We propose using an autonomous speechreading algorithm to help the deaf or hard-of-hearing by translating visual lip movements in live-time into coherent sentences. We accomplish this by using a supervised ensemble deep learning model to classify lip movements into phonemes, then stitch phonemes back into words. Our dataset consists of images of segmented mouths that are each labeled with a phoneme.

Modern software systems and products increasingly rely on machine learning models to make data-driven decisions based on interactions with users and systems, e.g., compute infrastructure. For broader adoption, this practice must (i) accommodate software engineers without ML backgrounds, and (ii) provide mechanisms to optimize for product goals. In this work, we describe general principles and a specific end-to-end ML platform, Looper, which offers easy-to-use APIs for decision-making and feedback collection. Looper supports the full end-to-end ML lifecycle from online data collection to model training, deployment, inference, and extends support to evaluation and tuning against product goals. We outline the platform architecture and overall impact of production deployment. We also describe the learning curve and summarize experiences from platform adopters.

Statistical modeling of outcomes based on a patient's presenting symptoms (symptomatology) can help deliver high quality care and allocate essential resources, which is especially important during the COVID-19 pandemic. Patient symptoms are typically found in unstructured notes, and thus not readily available for clinical decision making. In an attempt to fill this gap, this study compared two methods for symptom extraction from Emergency Department (ED) admission notes. Both methods utilized a lexicon derived by expanding The Center for Disease Control and Prevention's (CDC) Symptoms of Coronavirus list. The first method utilized a word2vec model to expand the lexicon using a dictionary mapping to the Uni ed Medical Language System (UMLS). The second method utilized the expanded lexicon as a rule-based gazetteer and the UMLS. These methods were evaluated against a manually annotated reference (f1-score of 0.87 for UMLS-based ensemble; and 0.85 for rule-based gazetteer with UMLS). Through analyses of associations of extracted symptoms used as features against various outcomes, salient risks among the population of COVID-19 patients, including increased risk of in-hospital mortality (OR 1.85, p-value < 0.001), were identified for patients presenting with dyspnea. Disparities between English and non-English speaking patients were also identified, the most salient being a concerning finding of opposing risk signals between fatigue and in-hospital mortality (non-English: OR 1.95, p-value = 0.02; English: OR 0.63, p-value = 0.01). While use of symptomatology for modeling of outcomes is not unique, unlike previous studies this study showed that models built using symptoms with the outcome of in-hospital mortality were not significantly different from models using data collected during an in-patient encounter (AUC of 0.9 with 95% CI of [0.88, 0.91] using only vital signs; AUC of 0.87 with 95% CI of [0.85, 0.88] using only symptoms). These findings indicate that prognostic models based on symptomatology could aid in extending COVID-19 patient care through telemedicine, replacing the need for in-person options. The methods presented in this study have potential for use in development of symptomatology-based models for other diseases, including for the study of Post-Acute Sequelae of COVID-19 (PASC).

Monotone Operator Equilibrium Models (monDEQs) represent a class of models combining the powerful deep equilibrium paradigm with convergence guarantees. Further, their inherent robustness to adversarial perturbations makes investigating their certifiability a promising research direction. Unfortunately, existing approaches are either imprecise or severely limited in scalability. In this work, we propose the first scalable and precise monDEQ verifier, based on two key ideas: (i) a novel convex relaxation enabling efficient inclusion checks, and (ii) non-trivial mathematical insights characterizing the fixpoint operations at the heart of monDEQs on sets rather than concrete inputs. An extensive evaluation of our verifier on the challenging $\ell_\infty$ perturbations demonstrates that it exceeds state-of-the-art performance in terms of speed (two orders of magnitude) and scalability (an order of magnitude) while yielding 25% higher certified accuracies on the same networks.