[Paper Summary] A new Google AI Research Study discovers Anomalous Data using Self Supervised Learning

New Google AI research introduces a 2-stage framework that uses recent progress on self-supervised representation learning and classic one-class algorithms. This framework is simple to train and shows SOTA performance on various benchmarks, including CIFAR, f-MNIST, Cat vs. Dog, and CelebA. Following that, they offer a novel representation learning approach for a practical industrial defect detection problem using the same architecture. On the MVTec benchmark, the framework achieves a new state-of-the-art.

Read More

[Paper Summary] Stanford Researchers use Deep Learning to predict Biological Structures, like RNAs, more accurately than ever before

Determination of 3D structures of biological molecules, like RNA’s, is difficult and often requires millions of dollars for such extensive efforts. Stanford University researchers have devised a new deep learning algorithm called ARES (Atomic Rotationally Equivalent Scorer) for overcoming this challenge by computationally forecasting accurate structures. 

Read More

Snapchat shows how it uses GPUs to accelerate Machine Learning (ML) Inferences

Machine learning (ML) and Artificial intelligence (AI) have transformed how industries make business decisions. Many firms are now leveraging ML and AI to compile consumer data and analyze and predict future consumer behaviour. This has allowed them to process high volumes of data rapidly and accurately and analyze valuable insights to take promising actions for their business. 

Read More

[Paper Summary] DGIST Team introduces, ‘DRANet’, an AI Neural Network module that can separate and convert Environmental Information

As a result of recent advances in Deep Learning (DL), deep learning neural networks (DNN) have been widely used to improve model performance in computer vision, natural language processing, and more. However, existing domain adaptation methods learn only associated features that share a domain. Thus domain gaps between data significantly degrade the existing model performance.

Read More

[Paper Summary] DeepMind Researchers introduce Epistemic Neural Networks (ENNs) for Uncertainty Modeling in Deep Learning

Deep learning algorithms are widely used in numerous AI applications because of their flexibility and computational scalability, making them suitable for complex applications. However, most deep learning methods today neglect epistemic uncertainty related to knowledge which is crucial for safe and fair AI. A new DeepMind study has provided a way for quantifying epistemic uncertainty, along with new perspectives on existing methods, all to improve our statistical knowledge of deep learning.

Read More

[Paper] Google AI introduces a pull-push Denoising Algorithm and Polyblur: A Deblurring Method that eliminates noise and blur in images

Despite the advances in imaging technology, image noise and restricted sharpness remain most critical factors for increasing the visual quality of an image. Noise can be linked to the particle nature of light, or electronic components may be introduced during the read-out process. A photographic editing process will then process the captured noisy signal via the camera image processor (ISP) and be enhanced, amplified, and distorted. Image blur may be caused by a wide range of phenomena, from inadvertent camera shake during capture, incorrect camera focusing, or sensor resolution due to the final lens aperture.

Read More

NVIDIA Launches TensorRT 8 that improves AI Inference Performance making Conversational AI smarter and more interactive from Cloud to Edge

Tensor 8

Today, NVIDIA released the eighth generation of the company’s AI software: TensorRT™ 8, which cuts inference time for language queries in half. This latest version of the software allows firms to deliver conversational AI applications with quality and responsiveness that was never possible before.  

Read More

[Paper Summary] IBM Researchers propose a Quantum Kernel Algorithm

Many quantum machine learning algorithms have been believed to provide exponential speed-ups over classical machine learning (ML) approaches, based on the assumption that classical data can be provided to the algorithm in the form of quantum states. Yet, no studies show whether a method exists that can efficiently provide data in this manner.

Read More

[Paper Summary] Cornell and Harvard University Researchers develops Correlation Convolutional Neural Networks (CCNN): To determine which Correlations are most important

team of researchers from Cornell and Harvard University introduces a novel approach to parse quantum matter and make crucial data distinctions. This proposed technique will enable researchers to decipher the most perplexing phenomena in the subatomic realm.

Read More

[Paper Summary] A novel Caltech Algorithm allows Autonomous Systems navigate themselves by referring the Surrounding Terrain, summer or winter

Car and Drone

The process employed in the algorithm is called ‘visual terrain-relative navigation’ (VTRN), which was first developed in the 1960s that helped the autonomous devices compare the nearby terrain to high-resolution satellite images to locate themselves.

Read More

EBRAINS Researchers introduce a Robot whose internal workings Mimic a Human Brain (with Video)

Ebrains

The human brain contains between 100 million and 100 billion neurons that process information from the senses and body and send messages back to the body. Thus, human intelligence is one of the most intriguing concepts many AI scientists are looking to replicate. A team of researchers at the new EBRAINS research infrastructure are building robots whose internal workings mimic the brain that would bring new concepts on the neural mechanisms.

Read More

[Paper Summary] Researchers From Allen Institute for AI releases AI2-THOR 3.0

ManipulaThor

The Allen Institute for AI (AI2) announces the release of AI2-THOR 3.0, which is an embodied AI framework. Embodied Artificial Intelligence is a sub-specialty of artificial intelligence at the intersection of robotics, computer vision, and natural language processing and is an emerging area of interest for researchers.

Read More

Researchers – Google, NVIDIA, Technical University of Munich (TUM), and Ludwig-Maximilians-University – introduce CodeTrans

Researchers from Google AI, NVIDIA, Ludwig-Maximilians-University, and Technical University of Munich (TUM) have recently published a paper describing CodeTrans, an encoder-decoder transformer model for the software engineering tasks domain. The proposed model explores the effectiveness of encoder-decoder transformer models for six software engineering tasks, including thirteen sub-tasks.

Read More

Google AI, DeepMind and the University of Toronto introduce DreamerV2

dreamer-v2

It is the first Reinforcement Learning (RL) agent based on the world model to attain human-level success on the Atari benchmark. It includes the second generation of the Dreamer agent who learns behaviors entirely within a world model’s latent space […]

Read More

Allen Institute For AI (AI2) Launches The 2.7.0 Version of AI2-THOR That Enables Users To Reduce Their Training Time Dramatically

AI2-THOR

Allen Institute for AI (AI2) has recently announced the 2.7.0 release of AI2-THOR. AI2-THOR is an open-source interactive environment for training and testing embodied AI. The 2.7.0 version of AI2-THOR contains several performance enhancements that can provide dramatic training time reductions. The new version introduces improvements to the IPC system between Unity/Python and serialization/deserialization format. It includes new actions that are much better to control the metadata. 

Read More

Facebook AI Introduces ‘ReBeL’: An Algorithm that generalizes the Paradigm of Self-Play Reinforcement Learning and search to Imperfect-Information Games

Most AI systems excel in generating specific responses to a particular problem. Today, AI can outperform humans in various fields. For AI to do any task it is presented with; it needs to generalize, learn, and understand new situations as they occur without supplementary guidance. However, as humans can recognize chess and Poker both as games in the broadest sense, teaching a single AI to play both is challenging. 

Read More