Multivariate-based algorithms are a powerful class of modern cryptographic algorithms - particularly, due to of their potential ability to secure against quantum computer attacks. They typically operate by using multivariate polynomials over finite fields for constructing public key schemes. Examples of such algorithms include Enhanced Tame Transformation Signature, Hidden Field Equations, Matsumoto-Imai Scheme, and Unbalanced Oil & Vinegar.
The core idea of MKPC algorithms is to ensure that one-directional compute (encryption & signature generation) is easy but inversion (decryption & signature verification) is NP-hard without a secret key. A central map is used to encode the multivariate polynomials across multiple variables. This map is then encrypted with two sets of affine transformations that serve as the trapdoor function.
Studied as part of Topology, mathematical knots are closed loops in 3D-space. The core idea of Knot Theory is to classify & manipulate knots to understand complex mathematical behavior. Knots are of various types - e.g., composite, prime, ribbon, satellite, torus, trivial (unknots), etc.
Knot Theory is extensively applied in different fields like biology (e.g., understanding processes like DNA replication), chemistry (e.g., development of new molecules), physics (e.g., study of electromagnetic field lines & quantum fields), and computer science (e.g., computational topology & visualization.)
Modern research in Knot Theory aims to address its unsolved problems (e.g., Slice-Ribbon Conjecture), study its application in quantum physics, and create efficient algorithms for classifying knots & for calculating knot invariants.
My team & I developed a multi-model framework to identify human emotions (and their intensity) from visual expressions & voice timbre. Apart from developing models with high accuracy, ensuring engineering efficiency (e.g., inferencing on resource-constrained systems) was also a key objective.
Facial inputs were processed by a hybrid architecture of standard CNNs, and Vision Transformers. Voice inputs were processed through Mel-Frequency Cepstral Coefficients, and a combination of RNNs & LSTMs. Post the input processing, information from both modes were fused together to generate the final emotion category & intensity level. The future direction of this research was to integrate EEG (electroencephalography) data with the audio-visual data to provide a more holistic understanding of emotions.
Deep Learning-based architectures have had a significant impact on computer vision, natural language processing, and other machine learning areas. However, the scenario is not so straightforward when it comes to Forecasting, an area where statistical and traditional machine learning models have generally outperformed other types
Volatility in financial markets, major fluctuations in weather conditions, the outbreak of infectious diseases, the unpredictability of the interactions among different animal species, and the intermittent failures of power grids – all of them are phenomena from diverse fields but have two things in common.
Dask is a Python framework for distributed and parallel computing. It offers low-level task APIs that extend the functionality of popular Python libraries, and high-level data-centric APIs that serve modern workloads such as machine learning. In particular, Dask serves to address the key limitations of
Amazon Prime Video’s March 2023 announcement of migrating from distributed microservices to a monolith architecture surprised many in the global developer community, and reignited the Monolith versus Microservices debate. A varied range of analyses surfaced after that – some supported the move, some inferred that
The Sun’s magnetic field goes through an approximately 11-year cycle during which it completely changes its polarity (i.e., the Sun’s South and North Poles trade places.) This phenomenon, called the Solar Cycle (or Schwabe cycle), leads to significant fluctuations in the frequency and intensity of
Minimum Spanning Tree (MST) offers powerful applications in a wide range of domains, including circuit design, computer science, electrical grids, financial markets, and telecom networks. They are also indirectly leveraged (e.g., as algorithm subroutines) for solving other critical problems, such as the Traveling Salesman or Minimum
Google introduced Spotlight, a foundational model for mobile UI modeling, particularly for tasks like command grounding, screen summarization, tappability prediction, and widget captioning. Traditional mobile UI design often uses the concept of view hierarchy information, but these view hierarchies are sometimes either not available, or
Microsoft introduced VALL-E, its neural codec language model for zero-shot Text-to-Speech Synthesis (TTS) that generates high-quality audio/speech with only a 3-second acoustic prompt (i.e., voice recording.) Unlike conventional models that consider TTS a continuous signal regression task, VALL-E approaches this as a conditional language modeling
Large Language Models (LLMs) are state-of-the-art today, and generally perform well for simple and low-interaction tasks, such as single-turn conversations, and command-and-response systems. However, their direct use is generally limited in the case of applications with complex and high-interaction tasks, such as multi-turn dialogue systems,
Generative AI technologies have garnered much attention over the last 24 to 30 months. Innovations like GPT-3 and 3.5 (ChatGPT), DALL-E2, and Stable Diffusion have occupied a large part of the public discourse. The developers of these technologies, and the entire ecosystems around them are
Built on top of Apache Lucene and first released in 2010, Elasticsearch has become the de-facto search technology for most enterprise use cases today. In conjunction with Beats, Kibana & Logstash (cumulatively, the Elastic Stack), it offers a tremendous value proposition for storing, searching, and
[siteorigin_widget class=”thinkup_builder_divider”][/siteorigin_widget] NeurIPS 2022 declared 13 submissions as outstanding papers from its main track. Is Out-of-distribution Detection Learnable? Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding Elucidating the Design Space of Diffusion-Based Generative Models ProcTHOR: Large-Scale Embodied AI Using Procedural Generation Using Natural Language and
To understand the Hubble Tension, we must first understand the Hubble Constant. The Hubble constant (H0) is a value that measures the rate of expansion of the universe. As we know, the universe is constantly expanding. However, what it is expanding into is still an
Researchers at the University of Oxford have achieved the quantum entanglement of two strontium-based optical clocks. While previous entanglement demonstrations were limited to microscopic distances, this one appears to be the first reported case of macroscopic entanglement. Simply put, quantum entanglement is a phenomenon that
3D Vision with Transformers: A Survey: https://arxiv.org/pdf/2208.04309v1.pdf Unifying Visual Perception by Dispersible Points Learning: https://arxiv.org/pdf/2208.08630v1.pdf ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild: https://arxiv.org/pdf/2208.11547v1.pdf ROLAND: Graph Learning Framework for Dynamic Graphs: https://arxiv.org/pdf/2208.07239v1.pdf Investigating Efficiently Extending Transformers for Long Input Summarization: https://arxiv.org/pdf/2208.04347v1.pdf Semantic-Aligned Matching
In a recent Nature Neuroscience paper, scientists from Boston University postulated that a specific type of brain stimulation called Transcranial Alternating Current Stimulation (tACS) could enable a path toward achieving long-lasting memory enhancement. They proposed that brain rhythms can be neuro-moderated through repetitive tACS to
High-Performance GPU-to-CPU Transpilation and Optimization via High-Level Parallel Constructs: https://arxiv.org/pdf/2207.00257.pdf Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding: https://arxiv.org/pdf/2207.02971v1.pdf More ConvNets in the 2020s: Scaling up Kernels Beyond 51 × 51 using Sparsity: https://arxiv.org/pdf/2207.03620v1.pdf Softmax-free Linear Transformers: https://arxiv.org/pdf/2207.03341v1.pdf
Scaling Vision Transformers: https://arxiv.org/pdf/2106.04560.pdf Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation: https://arxiv.org/pdf/2107.01378.pdf Risk-averse autonomous systems: A brief history and recent developments from the perspective of optimal control: https://arxiv.org/pdf/2109.08947.pdf LightSeq2: Accelerated Training for Transformer-based Models on GPUs: https://arxiv.org/pdf/2110.05722.pdf Conditionally Elicitable Dynamic Risk Measures For Deep
Computational Storytelling And Emotions: A Survey: https://arxiv.org/pdf/2205.10967.pdf Are Large Pre-Trained Language Models Leaking Your Personal Information?: https://arxiv.org/pdf/2205.12628.pdf FreDo: Frequency Domain-based Long-Term Time Series Forecasting: https://arxiv.org/pdf/2205.12301.pdf A Survey on Long-tailed Visual Recognition: https://arxiv.org/pdf/2205.13775.pdf Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors: https://arxiv.org/pdf/2205.12854.pdf On the
The AI that your company buys (or builds) may not be as secure as you think! As companies across the globe accelerate AI adoption, the corresponding security threats also continue to increase rapidly. More importantly, the potential consequences of security threats are becoming more severe
Multiview Transformers for Video Recognition: https://arxiv.org/pdf/2201.04288.pdf ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer: https://arxiv.org/pdf/2202.07305.pdf Privacy-preserving Anomaly Detection in Cloud Manufacturing via Federated Transformer: https://arxiv.org/pdf/2204.00843.pdf A Tour of Visualization Techniques for Computer Vision Datasets: https://arxiv.org/pdf/2204.08601.pdf Transfer Attacks Revisited: A Large-Scale Empirical Study in Real Computer Vision
Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism: https://arxiv.org/pdf/2203.05804.pdf Augmented Reality and Robotics: A Survey and Taxonomy for AR-enhanced Human-Robot Interaction and Robotic Interfaces: https://arxiv.org/pdf/2203.03254.pdf A Fast and Convergent Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization: https://arxiv.org/pdf/2203.16615.pdf Monte Carlo
Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review: https://arxiv.org/pdf/2202.12205.pdf NeuralFusion: Neural Volumetric Rendering under Human-object Interactions: https://arxiv.org/pdf/2202.12825.pdf Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection: https://arxiv.org/pdf/2202.07586.pdf Deep Recurrent Modelling of Granger Causality with Latent Confounding: https://arxiv.org/pdf/2202.11286.pdf
LaMDA: Language Models for Dialog Applications: https://arxiv.org/pdf/2201.08239v3.pdf Data-Driven Offline Optimization For Architecting Hardware Accelerators: https://arxiv.org/pdf/2110.11346v3.pdf Don’t Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis: https://arxiv.org/pdf/2202.07728v1.pdf Block-NeRF: Scalable Large Scene Neural View Synthesis: https://arxiv.org/pdf/2202.05263v1.pdf Maintaining fairness across distribution shift: do we have viable
A Systematic Exploration Of Reservoir Computing For Forecasting Complex Spatiotemporal Dynamics: https://arxiv.org/pdf/2201.08910.pdf FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting: https://arxiv.org/pdf/2201.12740.pdf Quantifying Epistemic Uncertainty in Deep Learning: https://arxiv.org/pdf/2110.12122.pdf What’s Wrong With Deep Learning In Tree Search For Combinatorial Optimization: https://arxiv.org/pdf/2201.10494.pdf A Leap among Quantum
Renewable energy has historically been costlier than fossilized energy. This is changing now. Lazard’s latest annual report on Levelized Cost of Energy Analysis highlighted that certain renewable energy technologies are becoming cost-competitive vis-à-vis conventional energy technologies. For example, see the chart below. Source: Levelized Cost
In 2017, Mozilla and others in the World Wide Web Consortium (W3C) released a new browser-based technology to enable high-performance applications on web pages. Initially based on Mozilla’s asm.js, this technology has evolved into the WebAssembly (WASM) that we know today. Not only has it
Lagrange Points (or L-points) recently came into the limelight during the launch of the James Webb Space Telescope (JWST). Named after the famous mathematician Joseph-Louis Lagrange, these are special points in space where the net gravitational forces of the earth and the sun (or to
Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning: https://arxiv.org/pdf/2201.05151.pdf A unified software/hardware scalable architecture for brain-inspired computing based on self-organizing neural models: https://arxiv.org/pdf/2201.02262v1.pdf MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs: https://arxiv.org/pdf/2201.02534v1.pdf Applications of Signature Methods to Market Anomaly Detection: https://arxiv.org/pdf/2201.02441v1.pdf
Traditional processor architectures have inherent limitations in fulfilling the high-performance needs of modern applications. This necessitated the development of domain-specific architectures and hardware accelerators. After a decade of development, RISC-V is now evolving as the preferred instruction-set-architecture for a wide range of modern processing workloads,
Exponential technologies like Artificial Intelligence, Blockchain and the Internet of Things (IoT) are creating significant breakthrough today. Lots of hype are woven around these technologies, huge investments are flowing into them, and new use cases are getting created on a regular basis. However, most organizations
A Globally Convergent Distributed Jacobi Scheme for Block-Structured Non-convex Constrained Optimization Problems: https://arxiv.org/pdf/2112.09027.pdf A Robust Optimization Approach to Deep Learning: https://arxiv.org/pdf/2112.09279.pdf A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation: https://arxiv.org/pdf/2112.09747.pdf A Survey of Natural Language Generation: https://arxiv.org/pdf/2112.11739.pdf Are Large-scale Datasets Necessary for
Simulation Intelligence: Towards A New Generation Of Scientific Methods: https://arxiv.org/pdf/2112.03235v1.pdf Information is Power: Intrinsic Control via Information Capture: https://arxiv.org/pdf/2112.03899v1.pdf GLaM: Efficient Scaling of Language Models with Mixture-of-Experts: https://arxiv.org/pdf/2112.06905v1.pdf Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning: https://arxiv.org/pdf/2112.03763v1.pdf Efficient Geometry-aware 3D Generative Adversarial Networks: https://arxiv.org/pdf/2112.07945v1.pdf
Covariate Shift in High-Dimensional Random Feature Regression: https://arxiv.org/pdf/2111.08234v1.pdf Improving Transferability of Representations via Augmentation-Aware Self-Supervision: https://arxiv.org/pdf/2111.09613v1.pdf GFlowNet Foundations: https://arxiv.org/pdf/2111.09266v1.pdf Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability: https://arxiv.org/pdf/2111.10752v1.pdf Benchmarking Detection Transfer Learning with Vision Transformers: https://arxiv.org/pdf/2111.11429v1.pdf Improved Knowledge Distillation via Adversarial Collaboration:
In the 1980s, space scientists and astronomers started talking about the existence of a new planet (called Planet X) to explain certain phenomena, such as the unexplained residuals in the orbit of Neptune. As new discoveries emerged over time, the idea gradually evolved and this
Gradients are Not All You Need: https://arxiv.org/pdf/2111.05803v1.pdf RAVE: A variational autoencoder for fast and high-quality neural audio synthesis: https://arxiv.org/pdf/2111.05011v1.pdf NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework: https://arxiv.org/pdf/2111.04130v1.pdf A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis: https://arxiv.org/pdf/2110.15678v2.pdf On Representation Knowledge
Shaking the foundations: delusions in sequence models for interaction and control: https://arxiv.org/pdf/2110.10819v1.pdf Understanding Dimensional Collapse in Contrastive Self-supervised Learning: https://arxiv.org/pdf/2110.09348v1.pdf SOFT: Softmax-free Transformer with Linear Complexity: https://arxiv.org/pdf/2110.11945v2.pdf Understanding How Encoder-Decoder Architectures Attend: https://arxiv.org/pdf/2110.15253v1.pdf Parameter Prediction for Unseen Deep Architectures: https://arxiv.org/pdf/2110.13100v1.pdf From Machine Learning to Robotics: Challenges
Multitask prompted training enables zero-shot task generalization: https://arxiv.org/pdf/2110.08207v1.pdf DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries: https://arxiv.org/pdf/2110.06922v1.pdf Object DGCNN: 3D Object Detection using Dynamic Graphs: https://arxiv.org/pdf/2110.06923v1.pdf Symbolic Knowledge Distillation: from General Language Models to Common sense Models: https://arxiv.org/pdf/2110.07178v1.pdf Graph Neural Networks with Learnable
Messaging systems form the backbone of many critical applications today. An important question for software architects and engineers is the selection of the right messaging system that can address multiple requirements like cross-platform communication, fault-tolerance, latency needs, and scalability. Several open-source and commercial messaging systems
The Astronomy and Astrophysics Decadal Survey is an exhaustive report on astronomy and astrophysics that the United States’ National Academy of Sciences publishes at the end of every decade. This report explains the current state of play in astronomy and astrophysics, and recommends the research
It is common knowledge that efficient architecture design is a key aspect of building any product/solution, including AI applications. However, in reality, it is often observed that companies pay limited attention to developing robust end-to-end architectures before initiating AI application development. This leads to several
The 12-Factor App Manifesto, released by Heroku in 2011, gradually became a gold standard in modern software development. While there are debates in some quarters today (and justifiably so) whether this manifesto represents the needs of modern SaaS applications, the fundamental philosophy of this approach
Modern software development is becoming more complex. The scope and scale of applications are becoming bigger, both in terms of functional and non-functional requirements. For instance, application teams want to release new innovations to their users at an accelerating pace, highly feature-rich user interfaces have
It has been over ninety years since the fundamental concept of Schwarzschild Wormholes (also called Einstein–Rosen Bridges) was first proposed. Over the years, scientists have been trying to determine if wormholes are actually a physical reality, and if they do exist, whether they are traversable
The speed of light is often considered to have a specific upper limit (c when light travels in a vacuum) but this limitation can be overcome under certain physical conditions. Pulses of light passing through specific materials can achieve group velocities that are higher or
Human perception is multimodal. We make sense of objects and events through multiple modalities (sensory organs), and that is why we excel in our understanding of the world around us. Similarly, in many real-world problems, Artificial Intelligence systems become more efficient when they process inputs
Researchers from MIT & IBM recently introduced CRL, a new self-supervised framework that learns task-agnostic visual representations in embodied environments. This approach is able to construct representations not only from unlabeled datasets, but also from environments. The CRL framework jointly learns a reinforcement learning policy,
Low-code engineering is not always the first option when companies decide to build new applications. Many engineering leaders are only partly aware of the capabilities of these platforms, or like to stick to the technologies that they know best. However, unless the goal is to
The European Union has just released its first legal framework for Artificial Intelligence. It covers a wide range of areas, including:▪︎ Defining the fundamental notion of an AI system.▪︎ Laying down the requirements for high risk AI systems, and obligations of their operators.▪︎ Prohibiting certain
The Beijing Academy of Artificial Intelligence (BAAI) released China’s first super-scale intelligence model system: WuDao 1.0. This is a combination of four very large-scale NLP models. WenYuan: China’s largest pre-training language model (supporting Chinese & English) for text categorization, sentiment analysis, reading comprehension, etc. It
Automated Machine Learning has come a long way since Google Brain introduced NAS in early 2017. Amazon’s AutoGluon, Google’s AutoMLZero, Salesforce’s TransmogrifAI, the AutoML features of Azure, H2O, Scikit-learn, Keras & others (TPOT, DataRobot, etc.) are witnessing increased adoption. Modern AutoML systems generally focus on hyper-parameter optimization (HPO), neural architecture search (NAS), model
Earlier this year, 55 researchers from 44 global institutions proposed GEM (Generation, Evaluation & Metrics), a new benchmark environment for Natural Language Generation. It evaluates models through an interactive result exploration system. This enables a much better understanding of model limitations & improvement opportunities, and
Design Patterns are reusable, formalized constructs that serve as templates to address common problems in designing efficient systems. These enable the development of high-performance, resilient & robust applications. Widely-used design patterns, especially from the object-oriented paradigm, include:▪︎ Behavioral Patterns: Command, Mediator, Memento, Observer, Visitor, etc.▪︎ Creational Patterns:
Object detection is one of the most fundamental problems in Computer Vision, and has powered many of the significant advances in this field. It has applications in a wide range of areas such as advertising, driverless cars, healthcare, robotics, security, and others. This quasi-technical paper
Emotion AI, also known as Affective Computing or Artificial Emotional Intelligence, is an interdisciplinary field that operates at the intersection of Behavioral Science, Cognitive Computing, Computer Science, Machine Learning, Neuroscience, Psychology, Signal Processing, and others. This is one of the rapidly evolving areas of AI
Philip E. Tetlock, one of the foremost global experts in forecasting behavior, conducted a comprehensive 20 year study of expert judgment in scientific literature, and concluded that the average expert performance was around the same as random guessing. Since this study was conducted between 1984
Extraordinary threats create extraordinary opportunities. Research & Development programs offer a great mechanism to explore/exploit such opportunities, thus enabling significant long-term value creation. At the same time, R&D functions are usually among the first to get financially impacted when a crisis strikes. Navigating R&D organizations
The COVID-19 pandemic is an earth-shattering, black swan event. Personal lives, societies and businesses are getting severely impacted. As governments, companies, institutions, and other organizations around the world shift their focus and resource allocation from their regular objectives to controlling this pandemic and its impact,
The materialization of systemic risk in any system leads to high instability and turbulence. This disruption is even greater in the case of complex systems. Power grid failures, financial market collapses, natural disasters, and global pandemics are some examples. This paper attempts to explain why
“You see, but you do not observe.” Sherlock Holmes, A Scandal in Bohemia. Knowledge, not mere data, is the real deal. Data is abundant in organizations, but not always in the structure and form that can be easily processed, analyzed and leveraged. As a result, companies
A common grievance of most enterprises is that while data is abundant, there is not enough knowledge. Data is the symbolic representation of the observable properties of real-world entities and, on its own, yields limited practical value. Knowledge, on the other hand, is ‘meaningful data’
An Asian publishing company embarked on a major transformation program to deploy AI-based analytics and business intelligence solutions across all their strategic business units. The program witnessed initial success during the proof-of-concept and early validation stages. This encouraged the company to initiate a phase-wise enterprise
“If you torture the data long enough, it will confess.” Ronald Coase, Nobel Prize Winner in Economics, 1991. Imagine a below-average shooter (the original story has a Texan) randomly firing at the side of a barn, and then painting bull’s-eyes around the tightest clusters of
Strategic Foresight refers to an organization’s ability to identify key drivers of change, and effectively prepare for multiple plausible alternative futures. The focus is not on predicting a singular future outcome, but on understanding how different versions of the future might shape up, and optimally
The Fourth Industrial Revolution (4IR) has begun. We are already witnessing massive disruptions in different forms and levels in most aspects of our businesses and lives. The determinants of business success are changing. Incremental and Non-R&D innovation will not be adequate for business leadership in
The broad theoretical foundations of Deep Learning were formed in the seventies and eighties, and evolved in the nineties and early 2000s. However, it was only in the early part of this decade that Deep Learning started emerging out of the confines of academia and
