Linking pages
- IBM Research Introduces Artificial Intelligence Unit (AIU): It's First Complete System-on-Chip Designed to Run and Train Deep Learning Models Faster and More Efficiently than a General-Purpose CPU - MarkTechPost https://www.marktechpost.com/2022/10/27/ibm-research-introduces-artificial-intelligence-unit-aiu-its-first-complete-system-on-chip-designed-to-run-and-train-deep-learning-models-faster-and-more-efficiently-than-a-general-purpose-cpu/ 10 comments
- Google AI Introduces 'TensorStore,' An Open-Source C++ And Python Library Designed For Reading And Writing Large Multi-Dimensional Arrays - MarkTechPost https://www.marktechpost.com/2022/09/25/google-ai-introduces-tensorstore-an-open-source-c-and-python-library-designed-for-reading-and-writing-large-multi-dimensional-arrays/ 2 comments
- Latest Artificial Intelligence (AI) Research Proposes the 'MrsFormer,' a Class of Efficient Transformers that Calculates the Approximation of the Attention Heads at Different Scales Using the Multiresolution-Head Attention (MrsHA) - MarkTechPost https://www.marktechpost.com/2022/11/16/latest-artificial-intelligence-ai-research-proposes-the-mrsformer-a-class-of-efficient-transformers-that-calculates-the-approximation-of-the-attention-heads-at-different-scales-using-the-multir/ 2 comments
- Researchers at Sony Computer Science Lab (CSL) have Developed a Machine Learning-based Model called 'SampleMatch,' that can Automatically Retrieve Drum Samples that Match a Specific Music Track from Large Archives - MarkTechPost https://www.marktechpost.com/2022/10/11/researchers-at-sony-computer-science-lab-csl-have-developed-a-machine-learning-based-model-called-samplematch-that-can-automatically-retrieve-drum-samples-that-match-a-specific-music/ 1 comment
- Researchers at Harvard Developed an Ionic Circuit Comprising Hundreds of Ionic Transistors and Performed a Core Process of Neural Network Computing in Water - MarkTechPost https://www.marktechpost.com/2022/10/20/researchers-at-harvard-developed-an-ionic-circuit-comprising-hundreds-of-ionic-transistors-and-performed-a-core-process-of-neural-network-computing-in-water/ 1 comment
- Meet FathomNet: An Open-Source Image Database That Uses Artificial Intelligence and Machine Learning Algorithms To Help Process The Backlog Of Visual Data For Understanding Our Ocean And Its Inhabitants - MarkTechPost https://www.marktechpost.com/2022/10/22/meet-fathomnet-an-open-source-image-database-that-uses-artificial-intelligence-and-machine-learning-algorithms-to-help-process-the-backlog-of-visual-data-for-understanding-our-ocean-and-its-inhabitan/ 1 comment
- Meta AI Introduces A Machine Learning-Based Model That Predicts Protein Folding 60x Faster Than The State of The Art - MarkTechPost https://www.marktechpost.com/2022/11/04/meta-ai-introduces-a-machine-learning-based-model-that-predicts-protein-folding-60x-faster-than-the-state-of-the-art/ 1 comment
- In a New Machine Learning Paper, Researchers From Deepmind Propose an approach 'Called Augmented Policy Cloning (APC),' to Support the Process of Data-Efficiently Learning from Parametric Experts - MarkTechPost https://www.marktechpost.com/2022/09/21/in-a-new-machine-learning-paper-researchers-from-deepmind-propose-an-approach-called-augmented-policy-cloning-apc-to-support-the-process-of-data-efficiently-learning-from-parametric-experts/ 0 comments
- Latest Machine Learning Research from Microsoft Exhibit a Neural Network Architecture that, in Polynomial Time, Learns as well as any Efficient Learning Algorithm Describable by a Constant-Sized Learning Algorithm - MarkTechPost https://www.marktechpost.com/2022/09/22/latest-machine-learning-research-from-microsoft-exhibit-a-neural-network-architecture-that-in-polynomial-time-learns-as-well-as-any-efficient-learning-algorithm-describable-by-a-constant-sized-learn/ 0 comments
- A new Speech Recognition Pipeline from CMU Research can recognize almost 2000 Languages without Audio - MarkTechPost https://www.marktechpost.com/2022/09/23/a-new-speech-recognition-pipeline-from-cmu-research-can-recognize-almost-2000-languages-without-audio/ 0 comments
- Google AI Introduces A Novel Reinforcement Learning (RL) Training Paradigm, 'ActorQ,' To Speed Up Actor-Learner Distributed RL Training - MarkTechPost https://www.marktechpost.com/2022/09/29/google-ai-introduces-a-novel-reinforcement-learning-rl-training-paradigm-actorq-to-speed-up-actor-learner-distributed-rl-training/ 0 comments
- Researchers at Peking University Open-Source 'CircuitNet,' a Dataset for Machine Learning Applications in Electronic Design Automation (EDA) - MarkTechPost https://www.marktechpost.com/2022/10/01/researchers-at-peking-university-open-source-circuitnet-a-dataset-for-machine-learning-applications-in-electronic-design-automation-eda/ 0 comments
- Researchers at MIT Startup 'DataCebo,' Introduce Synthetic Data Metrics: An Open-Source Python Library That Evaluates Synthetic Data By Comparing It To The Real Data That You're Trying To Mimic - MarkTechPost https://www.marktechpost.com/2022/10/05/researchers-at-mit-startup-datacebo-introduce-synthetic-data-metrics-an-open-source-python-library-that-evaluates-synthetic-data-by-comparing-it-to-the-real-data-that-youre-trying-to-mimic/ 0 comments
- Salesforce AI Research Proposes 'DeepTime,' A Deep Time-Index Based Model Trained Via A Meta-Learning Formulation To Automatically Learn A Representation Function From Time-Series Data - MarkTechPost https://www.marktechpost.com/2022/10/17/salesforce-ai-research-proposes-deeptime-a-deep-time-index-based-model-trained-via-a-meta-learning-formulation-to-automatically-learn-a-representation-function-from-time-series-data/ 0 comments
- Latest Machine Learning Research From CMU Introduces 'DASH,' a Differentiable NAS Algorithm that Computes the Mixture of Operations Using the Fourier Diagonalization of Convolution, Achieving an up-to-10x Search Time Speedup in Practice - MarkTechPost https://www.marktechpost.com/2022/10/19/latest-machine-learning-research-from-cmu-introduces-dash-a-differentiable-nas-algorithm-that-computes-the-mixture-of-operations-using-the-fourier-diagonalization-of-convolution-achieving-an-up/ 0 comments
- Google AI Propose A Patch-Based Multi-Scale Image Quality Transformer (MUSIQ) To Bypass The Convolutional Neural Network (CNN) Constraints On Fixed Input Size And Predict The Image Quality Effectively On Native-Resolution Images - MarkTechPost https://www.marktechpost.com/2022/10/25/google-ai-propose-a-patch-based-multi-scale-image-quality-transformer-musiq-to-bypass-the-convolutional-neural-network-cnn-constraints-on-fixed-input-size-and-predict-the-image/ 0 comments
- Researchers At IIIT Allahabad Propose T2CI GAN: A Deep Learning Model That Generates Compressed Images From Text - MarkTechPost https://www.marktechpost.com/2022/10/29/researchers-at-iiit-allahabad-propose-t2ci-gan-a-deep-learning-model-that-generates-compressed-images-from-text/ 0 comments
- Salesforce AI Developed FSNet (Fast and Slow Learning Network) for Deep Time-Series Forecasting, Which can Learn Deep Forecasting Models on the Fly in a Nonstationary Environment - MarkTechPost https://www.marktechpost.com/2022/11/02/salesforce-ai-developed-fsnet-fast-and-slow-learning-network-for-deep-time-series-forecasting-which-can-learn-deep-forecasting-models-on-the-fly-in-a-nonstationary-environment/ 0 comments
- According To This New AI Research At MIT, Machine Learning Models Trained On Synthetic Data Can Outperform Models Trained On Real Data In Some Cases, Which Could Eliminate Some Privacy, Copyright, And Ethical Concerns - MarkTechPost https://www.marktechpost.com/2022/11/07/according-to-this-new-ai-research-at-mit-machine-learning-models-trained-on-synthetic-data-can-outperform-models-trained-on-real-data-in-some-cases-which-could-eliminate-some-privacy-copyright-and/ 0 comments
- Meta AI Researchers Propose 'JUICER,' a Framework to Make Use of Both Binary and Free-Form Textual Human Feedback to Improve Dialogue Models After Deployment - MarkTechPost https://www.marktechpost.com/2022/11/08/meta-ai-researchers-propose-juicer-a-framework-to-make-use-of-both-binary-and-free-form-textual-human-feedback-to-improve-dialogue-models-after-deployment/ 0 comments
Linked pages
- [2210.17517] Lila: A Unified Benchmark for Mathematical Reasoning https://arxiv.org/abs/2210.17517 4 comments
- According To This New AI Research At MIT, Machine Learning Models Trained On Synthetic Data Can Outperform Models Trained On Real Data In Some Cases, Which Could Eliminate Some Privacy, Copyright, And Ethical Concerns - MarkTechPost https://www.marktechpost.com/2022/11/07/according-to-this-new-ai-research-at-mit-machine-learning-models-trained-on-synthetic-data-can-outperform-models-trained-on-real-data-in-some-cases-which-could-eliminate-some-privacy-copyright-and/ 0 comments
- Meta AI Researchers Propose 'JUICER,' a Framework to Make Use of Both Binary and Free-Form Textual Human Feedback to Improve Dialogue Models After Deployment - MarkTechPost https://www.marktechpost.com/2022/11/08/meta-ai-researchers-propose-juicer-a-framework-to-make-use-of-both-binary-and-free-form-textual-human-feedback-to-improve-dialogue-models-after-deployment/ 0 comments
- AI Researchers from the Netherlands Propose a Machine Learning-based Method to Design New Complex Metamaterials with Useful Properties - MarkTechPost https://www.marktechpost.com/2022/11/11/ai-researchers-from-the-netherlands-propose-a-machine-learning-based-method-to-design-new-complex-metamaterials-with-useful-properties/ 0 comments
- How Do DALL·E 2, Stable Diffusion, and Midjourney Work? - MarkTechPost https://www.marktechpost.com/2022/11/14/how-do-dall%c2%b7e-2-stable-diffusion-and-midjourney-work/ 0 comments
- Meet Diffusion-GAN: A Novel GAN Framework That Leverages A Forward Diffusion Chain To Generate Gaussian-Mixture Distributed Instance Noise - MarkTechPost https://www.marktechpost.com/2022/11/15/meet-diffusion-gan-a-novel-gan-framework-that-leverages-a-forward-diffusion-chain-to-generate-gaussian-mixture-distributed-instance-noise/ 0 comments
- Līla: A Unified Benchmark for Mathematical Reasoning | by Matthew Finlayson | Nov, 2022 | AI2 Blog https://blog.allenai.org/l%C4%ABla-a-unified-benchmark-for-mathematical-reasoning-1e505abe69cd 0 comments