Collaborating Authors

Neural Networks

Squawking Chickens will Tell You if They are Sick and AI is Here to Listen


Artificial intelligence (AI) has started focusing on animal welfare including poultry farms in recent times. Farmers can leverage AI for its voice technology with a deep learning tool known as a bird-brained bot to gain information regarding baby chicks and chickens on their farms. AI can help to detect squawking chickens and get them out of distress by enhancing their health or physical conditions. The bird-brained bot is developed for the well-being of squawking chickens by listening to them carefully. The deep learning tool with the integrated voice technology can help to determine their issues and happiness with their squawking patterns. Instagram's New AI is the Common Creep Tech that Happily Invades Your Privacy But Why are Other Nations Worried?

Machine Learning Zuihitsu -- VII


Variational Autoencoders (VAEs) can be considered one of the relatively underrated architectures of the Deep Learning literature. Since their introduction by seminal paper [Kingma et al., 2013], various extensions are developed on top of this vanilla model improving its performance and diversifying use cases. However, with a quick github search, one can deduce that practical implementations of VAEs are somehow redundant, if not limited. In this article, I would like to share my personal experience with VAEs, which provided me a competitive edge with their robust and accurate high dimensional embedding abilities both in unsupervised, but also supervised tasks. Unfortunately, as just being said, I found that it is particularly hard for a newcomer to the subject to find an accurate practical plug-and-play solution.

Kaspersky buys stake in neuromorphic computing company - IT-Online


Kaspersky has become a shareholder of Motive Neuromorphic Technologies, a company specialising in neuromorphic computing technologies, with a 15% stake. The organisations' joint development efforts are aimed at creating new opportunities for machine learning-based solutions: self-learning systems and smart devices of the future. In 2019, Kaspersky concluded a cooperation agreement with Motive NT, joining it in the development of the Altai neuromorphic processor, which accelerates the hardware of systems using Machine Learning. During the partnership, the companies' specialists together produced their first batch of neuromorphic processors, developed a software package for them and successfully confirmed their performance on measures of speed and energy efficiency through experimentation. The companies are currently working on developing a second version of the neuromorphic processor, as well as searching for technological partners to establish joint pilot projects using the Altai neurochip.

We Asked GPT-3 to Write an Academic Paper about Itself--Then We Tried to Get It Published


On a rainy afternoon earlier this year, I logged in to my OpenAI account and typed a simple instruction for the company's artificial intelligence algorithm, GPT-3: Write an academic thesis in 500 words about GPT-3 and add scientific references and citations inside the text. As it started to generate text, I stood in awe. Here was novel content written in academic language, with well-grounded references cited in the right places and in relation to the right context. It looked like any other introduction to a fairly good scientific publication. Given the very vague instruction I provided, I didn't have any high expectations: I'm a scientist who studies ways to use artificial intelligence to treat mental health concerns, and this wasn't my first experimentation with AI or GPT-3, a deep-learning algorithm that analyzes a vast stream of information to create text on command. Yet there I was, staring at the screen in amazement.

ETH Zurich AI Researchers Introduce 'tntorch': a PyTorch-Powered Tensor Learning Python …


Tensor decompositions are crucial in machine learning because they factorize the weights of neural networks.

Meet 'NeuraLight': An Israel-based AI Startup That Tracks Neurological Disorders With an …


Their patented computer vision and deep learning algorithms extract all necessary oculometric signals from facial footage shot with a typical webcam …

Top Guinness world records in AI


Artificial intelligence is growing at record-breaking speed, literally. Thanks to exponential development, AI has made its way to the Guinness book of world records. Below is a list of records in the AI domain. What started as a simple Bot Camp program became a world record for the largest artificial intelligence programming lesson. Capital One Services LLC hosted this camp as part of its Future Edge DFW initiative in Dallas, Texas, USA, on April 17 2019.

Reports of the Workshops Held at the 2022 AAAI Conference on Artificial Intelligence

Interactive AI Magazine

The Workshop Program of the Association for the Advancement of Artificial Intelligence's Thirty-Sixth Conference on Artificial Intelligence was held virtually from February 22 – March 1, 2022. There were thirty-nine workshops in the program: Adversarial Machine Learning and Beyond, AI for Agriculture and Food Systems, AI for Behavior Change, AI for Decision Optimization, AI for Transportation, AI in Financial Services: Adaptiveness, Resilience & Governance, AI to Accelerate Science and Engineering, AI-Based Design and Manufacturing, Artificial Intelligence for Cyber Security, Artificial Intelligence for Education, Artificial Intelligence Safety, Artificial Intelligence with Biased or Scarce Data, Combining Learning and Reasoning: Programming Languages, Formalisms, and Representations, Deep Learning on Graphs: Methods and Applications, DE-FACTIFY: Multi-Modal Fake News and Hate-Speech Detection, Dialog System Technology Challenge, Engineering Dependable and Secure Machine Learning Systems, Explainable Agency in Artificial Intelligence, Graphs and More Complex Structures for Learning and Reasoning, Health Intelligence, Human-Centric Self-Supervised Learning, Information-Theoretic Methods for Casual Inference and Discovery, Information Theory for Deep Learning, Interactive Machine Learning, Knowledge Discovery from Unstructured Data in Financial Services, Learning Network Architecture during Training, Machine Learning for Operations Research, Optimal Transports and Structured Data Modeling, Practical Deep Learning in the Wild, Privacy-Preserving Artificial Intelligence, Reinforcement Learning for Education: Opportunities and Challenges, Reinforcement Learning in Games, Robust Artificial Intelligence System Assurance, Scientific Document Understanding, Self-Supervised Learning for Audio and Speech Processing, Trustable, Verifiable and Auditable Federated Learning, Trustworthy AI for Healthcare, Trustworthy Autonomous Systems Engineering, and Video Transcript Understanding. This report contains summaries of the workshops, which were submitted by most, but not all the workshop chairs.

Deep Learning to See: Towards New Foundations of Computer Vision


The remarkable progress in computer vision over the last few years is, by and large, attributed to deep learning, fueled by the availability of huge sets of labeled data, and paired with the explosive growth of the GPU paradigm. While subscribing to this view, this book criticizes the supposed scientific progress in the field and proposes the investigation of vision within the framework of information-based laws of nature. Specifically, the present work poses fundamental questions about vision that remain far from understood, leading the reader on a journey populated by novel challenges resonating with the foundations of machine learning. The central thesis is that for a deeper understanding of visual computational processes, it is necessary to look beyond the applications of general purpose machine learning algorithms and focus instead on appropriate learning theories that take into account the spatiotemporal nature of the visual signal.

Localization and classification of structural damage using deep learning single-channel signal-based measurement


Novel 1D CNN named BuildingNet learns features & classifies real-time damage in various scenarios. Vibration-based DL real-time methodology analyzes damage with high precision and fast computational time. Single-channel vibration-based detector evaluates structural safety via an economical and practical SHM system. Model's efficiency & robustness indicated by use of 20% random Gaussian noise & validated on case study. Diligent damage identification is a core thrust of structural health monitoring (SHM).