Partial differential equations can describe everything from planetary motion to plate tectonics, but they’re notoriously hard to solve.
… But partial differential equations, or PDEs, are also kind of magical. They’re a category of math equations that are really good at describing change over space and time, and thus very handy for describing the physical phenomena in our universe. … The catch is PDEs are notoriously hard to solve.
… Now researchers at Caltech have introduced a new deep-learning technique for solving PDEs that is dramatically more accurate than deep-learning methods developed previously. Read More
Tag Archives: Deep Learning
Dive into Deep Learning
This book represents our attempt to make deep learning approachable, teaching you the concepts,the context, and the code. The book teaches most concepts just in time, interleaving runnable code with the material.
Learn more: https://amazon.science/latest-news/amazon-scientists-author-popular-deep-learning-book
★★★★FREE Download: https://d2l.ai/d2l-en.pdf
Deep Learning Modeling of the Limit Order Book: A Comparative Perspective
The present work addresses theoretical and practical questions in the domain of Deep Learning for High Frequency Trading, with a thorough review and analysis of the literature and state-of-the-art models. Random models, Logistic Regressions, LSTMs, LSTMs equipped with an Attention mask, CNN-LSTMs and MLPs are compared on the same tasks, feature space, and dataset and clustered according to pairwise similarity and performance metrics. The underlying dimensions of the modeling techniques are hence investigated to understand whether these are intrinsic to the Limit Order Book’s dynamics. It is possible to observe that the Multilayer Perceptron performs comparably to or better than state-of-the-art CNN-LSTM architectures indicating that dynamic spatial and temporaldimensions are a good approximation of the LOB’s dynamics, but not necessarily the true underlying dimensions. Read More
#investing, #deep-learningTraditional vs Deep Learning Algorithms used in BlockChain in Retail Industry
This blog highlights different ML algorithms used in blockchain transactions with a special emphasis on bitcoins in retail payments. This blog is structured as follows:
— Overview of the role of blockchain in the retail industry.
— Different traditional (SecureSVM, Bagging, BoostingClustering) vs deep learning algorithms (LSTM, CNN, and GAN) used in bitcoin retail payments.
Read More
MIT researchers warn that deep learning is approaching computational limits
We’re approaching the computational limits of deep learning. That’s according to researchers at the Massachusetts Institute of Technology, MIT-IBM Watson AI Lab, Underwood International College, and the University of Brasilia, who found in a recent study that progress in deep learning has been “strongly reliant” on increases in compute. It’s their assertion that continued progress will require “dramatically” more computationally efficient deep learning methods, either through changes to existing techniques or via new as-yet-undiscovered methods. Read More
IoT Anomaly detection – algorithms, techniques and open source implementation
Anomaly detection for IoT is one of the archetypal applications for IoT.
Anomaly detection techniques are also used outside of IoT.
In my teaching at the #universityofoxford – we use anomaly detection as a use case because it brings together many of the intricacies for IoT and also demonstrates the use of multiple machine learning and deeplearning algorithms.
Long term, I am exploring the idea of creating an open source anomaly detector for IoT – both for my students and in general. Read More
Shortcut Learning in Deep Neural Networks
Deep learning has triggered the current rise of artificial intelligence and is the work horse of today’s machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently come into focus. In this perspective we seek to distil how many of deep learning’s problem can be seen as different symptoms of the same underlying problem:shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in Comparative Psychology, Education and Linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike. Based on these observations, we develop a set of recommendations for model interpretation and benchmarking,highlighting recent advances in machine learning to improve robustness and transfer ability from the lab to real-world applications. Read More
Learning To Explore Using Active Neural Slam
This work presents a modular and hierarchical approach to learn policies for exploring 3D environments, called ‘Active Neural SLAM’. Our approach leverages the strengths of both classical and learning-based methods, by using analytical path planners with learned SLAM module, and global and local policies. The use of learning provides flexibility with respect to input modalities (in the SLAM module), leverages structural regularities of the world (in global policies), and provides robustness to errors in state estimation (in local policies). Such use of learning within each module retains its benefits, while at the same time, hierarchical decomposition and modular training allow us to sidestep the high sample complexities associated with training end-to-end policies. Our experiments in visually and physically realistic simulated 3D environments demonstrate the effectiveness of our approach over past learning and geometry-based approaches. The proposed model can also be easily transferred to the PointGoal task and was the winning entry of the CVPR 2019 Habitat PointGoal Navigation Challenge. Read More
#deep-learningComputational predictions of protein structures associated with COVID-19
The scientific community has galvanised in response to the recent COVID-19 outbreak, building on decades of basic research characterising this virus family. Labs at the forefront of the outbreak response shared genomes of the virus in open access databases, which enabled researchers to rapidly develop tests for this novel pathogen. Other labs have shared experimentally-determined and computationally-predicted structures of some of the viral proteins, and still others have shared epidemiological data. We hope to contribute to the scientific effort using the latest version of our AlphaFold system by releasing structure predictions of several under-studied proteins associated with SARS-CoV-2, the virus that causes COVID-19. We emphasise that these structure predictions have not been experimentally verified, but hope they may contribute to the scientific community’s interrogation of how the virus functions, and serve as a hypothesis generation platform for future experimental work in developing therapeutics. We’re indebted to the work of many other labs: this work wouldn’t be possible without the efforts of researchers across the globe who have responded to the COVID-19 outbreak with incredible agility. Read More
#deep-learning
Rick's Cafe AI 