BibSonomy bookmarks for /user/analyst/2021https://www.bibsonomy.org/user/analyst/2021BibSonomy RSS Feed for /user/analyst/2021PyBullet in a colab | Bullet Real-Time Physics Simulationhttps://pybullet.org/wordpress/index.php/2021/04/15/pybullet-in-a-colab/analyst2024-02-21T10:24:32+01:002021 colab manipulator pybullet robotics simulation <a itemprop="url" data-versiondate="2024-02-21T10:24:32+01:00" href="https://pybullet.org/wordpress/index.php/2021/04/15/pybullet-in-a-colab/" rel="nofollow" class="description-link">https://pybullet.org/wordpress/index.php/2021/04/15/pybullet-in-a-colab/</a>Moral duty and legal obligation of son to provide sustenance to parents in old age, says Supreme Court | Delhi News - Times of IndiaThe Supreme Court on Tuesday scolded a truant son for attempting every possible ruse to resist payment of Rs 10,000 monthly maintenance to his 72-yearhttps://timesofindia.indiatimes.com/city/delhi/sc-moral-duty-and-legal-obligation-of-son-to-provide-sustenance-to-parents-in-old-age/articleshow/87876707.cmsanalyst2022-05-19T05:45:10+02:002021 article news <span itemprop="description">The Supreme Court on Tuesday scolded a truant son for attempting every possible ruse to resist payment of Rs 10,000 monthly maintenance to his 72-year</span>Piecewise-constant Neural ODEshttps://greydanus.github.io/2021/06/11/piecewise-nodes/analyst2022-05-11T08:41:42+02:002021 article blog deep-learning ode <a itemprop="url" data-versiondate="2022-05-11T08:41:42+02:00" href="https://greydanus.github.io/2021/06/11/piecewise-nodes/" rel="nofollow" class="description-link">https://greydanus.github.io/2021/06/11/piecewise-nodes/</a>Robotics Today - A Series of Technical Talkshttps://roboticstoday.github.io/analyst2022-01-22T12:27:39+01:002020 2021 collection conference lecture robotics video <a itemprop="url" data-versiondate="2022-01-22T12:27:39+01:00" href="https://roboticstoday.github.io/" rel="nofollow" class="description-link">https://roboticstoday.github.io/</a>Computer Graphics - 2021 Spring | GISTCGLab (since 2016.09) focuses on conducting research on photorealistic rendering, which includes a variety of optimization techniques for ray tracing. The main applications of photorealistic rendering are CG movies, animations, 3D games and immersive technology (AR and VR).https://cglab.gist.ac.kr/courses/spring2021CG/analyst2022-01-05T20:35:41+01:002021 graphics rendering <span itemprop="description">CGLab (since 2016.09) focuses on conducting research on photorealistic rendering, which includes a variety of optimization techniques for ray tracing. The main applications of photorealistic rendering are CG movies, animations, 3D games and immersive technology (AR and VR).</span>Illustrating Math @ PCMI — Summer 2021Erasing the artificial divide between research and outreach.http://illustratingmath-pcmi.org/analyst2021-11-13T10:34:22+01:002021 geometry mathematics princeton research summer-school visualization <span itemprop="description">Erasing the artificial divide between research and outreach.</span>Toward optimal probabilistic active learning using a Bayesian approach | SpringerLinkGathering labeled data to train well-performing machine learning models is one of the critical challenges in many applications. Active learning aims at redhttps://link.springer.com/article/10.1007/s10994-021-05986-9analyst2021-08-22T08:54:57+02:002021 bayesian machine-learning springer <span itemprop="description">Gathering labeled data to train well-performing machine learning models is one of the critical challenges in many applications. Active learning aims at red</span>6.874 Computational Systems Biology: Deep Learning in the Life Sciences - Spring 2021Course materials and notes for MIT class 6.802 / 6.874 / 20.390 / 20.490 / HST.506 Computational Systems Biology: Deep Learning in the Life Scienceshttps://mit6874.github.io/analyst2021-07-16T10:40:31+02:002021 biology course mit <span itemprop="description">Course materials and notes for MIT class 6.802 / 6.874 / 20.390 / 20.490 / HST.506 Computational Systems Biology: Deep Learning in the Life Sciences</span>CS590: Cloud-Native Database Systems | Purduehttps://www.cs.purdue.edu/homes/csjgwang/cloudb/analyst2021-07-05T08:38:16+02:002021 cloud course database <a itemprop="url" data-versiondate="2021-07-05T08:38:16+02:00" href="https://www.cs.purdue.edu/homes/csjgwang/cloudb/" rel="nofollow" class="description-link">https://www.cs.purdue.edu/homes/csjgwang/cloudb/</a>New Spaces in Mathematics and Physics | Not Even Wronghttps://www.math.columbia.edu/~woit/wordpress/?p=12238analyst2021-06-29T07:09:26+02:002021 book download geometry topology <a itemprop="url" data-versiondate="2021-06-29T07:09:26+02:00" href="https://www.math.columbia.edu/~woit/wordpress/?p=12238" rel="nofollow" class="description-link">https://www.math.columbia.edu/~woit/wordpress/?p=12238</a>The real urban jungle: how ancient societies reimagined what cities could be | Cities | The GuardianThey may be vine-smothered ruins today, but the lost cities of the ancient tropics still have a lot to teach us about how to live alongside naturehttps://www.theguardian.com/news/2021/jun/22/the-real-urban-jungle-how-ancient-societies-reimagined-what-cities-could-beanalyst2021-06-29T04:52:34+02:002021 architecture news <span itemprop="description">They may be vine-smothered ruins today, but the lost cities of the ancient tropics still have a lot to teach us about how to live alongside nature</span>I have ‘pandemic brain’. Will I ever be able to concentrate again? | Life and style | The GuardianWhen lockdown hit, I became distracted, unfocused – and overwhelmed. But there are ways to recoverhttps://www.theguardian.com/us-news/2021/jun/24/pandemic-brain-covid-coronavirus-fog-concentrateanalyst2021-06-28T08:37:29+02:002021 brain covid news <span itemprop="description">When lockdown hit, I became distracted, unfocused – and overwhelmed. But there are ways to recover</span>Yoshua Bengio Team Designs Consciousness-Inspired Planning Agent for Model-Based RL | by Synced | SyncedReview | Jun, 2021 | MediumA research team from McGill University, Université de Montréal, DeepMind and Mila presents an end-to-end, model-based deep reinforcement learning (RL) agent that dynamically attends to relevant parts of its environments to facilitate out-of-distribution (OOD) and systematic generalization.https://medium.com/syncedreview/yoshua-bengio-team-designs-consciousness-inspired-planning-agent-for-model-based-rl-501b4d7e80f5analyst2021-06-25T17:06:16+02:002021 machine-learning reinforcement-learning <span itemprop="description">A research team from McGill University, Université de Montréal, DeepMind and Mila presents an end-to-end, model-based deep reinforcement learning (RL) agent that dynamically attends to relevant parts of its environments to facilitate out-of-distribution (OOD) and systematic generalization.</span>Daily PapersFind latest and trending machine learning papershttps://papers.labml.ai/papers/dailyanalyst2021-06-25T17:05:44+02:002021 collection machine-learning paper recommendation <span itemprop="description">Find latest and trending machine learning papers</span>Thinking Like Transformershttps://papers.labml.ai/paper/2106.06981analyst2021-06-25T17:05:01+02:002021 machine-learning paper research <a itemprop="url" data-versiondate="2021-06-25T17:05:01+02:00" href="https://papers.labml.ai/paper/2106.06981" rel="nofollow" class="description-link">https://papers.labml.ai/paper/2106.06981</a>Evolution, rewards, and artificial intelligence – TechTalksA paper by DeepMind scientist triggered much debate about the path to artificial intelligence. Here, we'll try to draw the line between theory and practice.https://bdtechtalks.com/2021/06/17/evolution-rewards-artificial-intelligence/analyst2021-06-25T17:04:28+02:002021 article blog google lecture reinforcement-learning <span itemprop="description">A paper by DeepMind scientist triggered much debate about the path to artificial intelligence. Here, we'll try to draw the line between theory and practice.</span>AI Researchers Including Yoshua Bengio, Introduce A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning | MarkTechPosthttps://www.marktechpost.com/2021/06/18/ai-researchers-including-yoshua-bengio-introduce-a-consciousness-inspired-planning-agent-for-model-based-reinforcement-learning/?fbclid=IwAR2It8RaYfX_pQ8XXZTZPARacjVZOL8OUiEmIqg5A7niuZ5wVG46GbrV0moanalyst2021-06-25T17:02:52+02:002021 article blog machine-learning news <a itemprop="url" data-versiondate="2021-06-25T17:02:52+02:00" href="https://www.marktechpost.com/2021/06/18/ai-researchers-including-yoshua-bengio-introduce-a-consciousness-inspired-planning-agent-for-model-based-reinforcement-learning/?fbclid=IwAR2It8RaYfX_pQ8XXZTZPARacjVZOL8OUiEmIqg5A7niuZ5wVG46GbrV0mo" rel="nofollow" class="description-link">https://www.marktechpost.com/2021/06/18/ai-researchers-including-yoshua-bengio-introduce-a-consciousness-inspired-planning-agent-for-model-based-reinforcement-learning/?fbclid=IwAR2It8RaYfX_pQ8XXZTZPARacjVZOL8OUiEmIqg5A7niuZ5wVG46GbrV0mo</a>Teaching recurrent neural networks to infer global temporal structure from local examples | Nature Machine IntelligenceThe ability to store and manipulate information is a hallmark of computational systems. Whereas computers are carefully engineered to represent and perform mathematical operations on structured data, neurobiological systems adapt to perform analogous functions without needing to be explicitly engineered. Recent efforts have made progress in modelling the representation and recall of information in neural systems. However, precisely how neural systems learn to modify these representations remains far from understood. Here, we demonstrate that a recurrent neural network (RNN) can learn to modify its representation of complex information using only examples, and we explain the associated learning mechanism with new theory. Specifically, we drive an RNN with examples of translated, linearly transformed or pre-bifurcated time series from a chaotic Lorenz system, alongside an additional control signal that changes value for each example. By training the network to replicate the Lorenz inputs, it learns to autonomously evolve about a Lorenz-shaped manifold. Additionally, it learns to continuously interpolate and extrapolate the translation, transformation and bifurcation of this representation far beyond the training data by changing the control signal. Furthermore, we demonstrate that RNNs can infer the bifurcation structure of normal forms and period doubling routes to chaos, and extrapolate non-dynamical, kinematic trajectories. Finally, we provide a mechanism for how these computations are learned, and replicate our main results using a Wilson–Cowan reservoir. Together, our results provide a simple but powerful mechanism by which an RNN can learn to manipulate internal representations of complex information, enabling the principled study and precise design of RNNs. Recurrent neural networks (RNNs) can learn to process temporal information, such as speech or movement. New work makes such approaches more powerful and flexible by describing theory and experiments demonstrating that RNNs can learn from a few examples to generalize and predict complex dynamics including chaotic behaviour.https://www.nature.com/articles/s42256-021-00321-2analyst2021-06-02T10:29:09+02:002021 article deep-learning nature research rnn <span itemprop="description">The ability to store and manipulate information is a hallmark of computational systems. Whereas computers are carefully engineered to represent and perform mathematical operations on structured data, neurobiological systems adapt to perform analogous functions without needing to be explicitly engineered. Recent efforts have made progress in modelling the representation and recall of information in neural systems. However, precisely how neural systems learn to modify these representations remains far from understood. Here, we demonstrate that a recurrent neural network (RNN) can learn to modify its representation of complex information using only examples, and we explain the associated learning mechanism with new theory. Specifically, we drive an RNN with examples of translated, linearly transformed or pre-bifurcated time series from a chaotic Lorenz system, alongside an additional control signal that changes value for each example. By training the network to replicate the Lorenz inputs, it learns to autonomously evolve about a Lorenz-shaped manifold. Additionally, it learns to continuously interpolate and extrapolate the translation, transformation and bifurcation of this representation far beyond the training data by changing the control signal. Furthermore, we demonstrate that RNNs can infer the bifurcation structure of normal forms and period doubling routes to chaos, and extrapolate non-dynamical, kinematic trajectories. Finally, we provide a mechanism for how these computations are learned, and replicate our main results using a Wilson–Cowan reservoir. Together, our results provide a simple but powerful mechanism by which an RNN can learn to manipulate internal representations of complex information, enabling the principled study and precise design of RNNs. Recurrent neural networks (RNNs) can learn to process temporal information, such as speech or movement. New work makes such approaches more powerful and flexible by describing theory and experiments demonstrating that RNNs can learn from a few examples to generalize and predict complex dynamics including chaotic behaviour.</span>Top 10 Databases to Use in 2021. MySQL, Oracle, PostgreSQL, Microsoft… | by Md Kamaruzzaman | Towards Data ScienceDatabases are the cornerstone of any Software Applications. You will need one or more databases to develop almost all kind of Software Applications: Web, Enterprise, Embedded Systems, Real-Time…https://towardsdatascience.com/top-10-databases-to-use-in-2021-d7e6a85402baanalyst2021-06-02T09:59:47+02:002021 article blog collection database recommendation <span itemprop="description">Databases are the cornerstone of any Software Applications. You will need one or more databases to develop almost all kind of Software Applications: Web, Enterprise, Embedded Systems, Real-Time…</span>After Centuries, a Seemingly Simple Math Problem Gets an Exact SolutionQuanta Magazinehttps://www.quantamagazine.org/after-centuries-a-seemingly-simple-math-problem-gets-an-exact-solution-20201209/analyst2021-05-12T03:07:29+02:002021 geometry magazine mathematics problem <span itemprop="description">Quanta Magazine</span>