Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images
Change detection has been a hotspot in remote sensing technology for a long time. With the increasing availability of multi-temporal remote sensing images, numerous change detection algorithms have been proposed. Among these methods, image transformation methods with feature extraction and mapping could effectively highlight the changed information and thus has better change detection performance. However, changes of multi-temporal images are usually complex, existing methods are not effective enough. In recent years, deep network has shown its brilliant performance in many fields including feature extraction and projection. Therefore, in this paper, based on deep network and slow feature analysis (SFA) theory, we proposed a new change detection algorithm for multi-temporal remotes sensing images called Deep Slow Feature Analysis (DSFA). In DSFA model, two symmetric deep networks are utilized for projecting the input data of bi-temporal imagery. Then, the SFA module is deployed to suppress the unchanged components and highlight the changed components of the transformed features. The CVA pre-detection is employed to find unchanged pixels with high confidence as training samples. Finally, the change intensity is calculated with chi-square distance and the changes are determined by thresholding algorithms. The experiments are performed on two real-world data sets. The overall detection accuracies of our proposed method on two experiments are 97.64% and 94.32%, respectively. The visual comparison and quantitative evaluation have both shown that DSFA could outperform the other state-of-the-art algorithms, including other SFA-based algorithms.
Essential guidelines for computational method benchmarking
In computational biology and other sciences, researchers are frequently faced with a choice between several computational methods for performing data analyses. Benchmarking studies aim to rigorously compare the performance of different methods using well-characterized benchmark datasets, to determine the strengths of each method or to provide recommendations regarding the best choice of method for an analysis. However, benchmarking studies must be carefully designed and implemented to provide accurate and unbiased results. Here, we summarize key practical guidelines and recommendations for performing high-quality benchmarking analyses, based on our own experiences in computational biology.
EnsNet: Ensconce Text in the Wild
A new method is proposed for removing text from natural images. The challenge is to first accurately localize text on the stroke-level and then replace it with a visually plausible background. Unlike previous methods that require image patches to erase scene text, our method, namely ensconce network (EnsNet), can operate end-to-end on a single image without any prior knowledge. The overall structure is an end-to-end trainable FCN-ResNet-18 network with a conditional generative adversarial network (cGAN). The feature of the former is first enhanced by a novel lateral connection structure and then refined by four carefully designed losses: multiscale regression loss and content loss, which capture the global discrepancy of different level features; texture loss and total variation loss, which primarily target filling the text region and preserving the reality of the background. The latter is a novel local-sensitive GAN, which attentively assesses the local consistency of the text erased regions. Both qualitative and quantitative sensitivity experiments on synthetic images and the ICDAR 2013 dataset demonstrate that each component of the EnsNet is essential to achieve a good performance. Moreover, our EnsNet can significantly outperform previous state-of-the-art methods in terms of all metrics. In addition, a qualitative experiment conducted on the SMBNet dataset further demonstrates that the proposed method can also preform well on general object (such as pedestrians) removal tasks. EnsNet is extremely fast, which can preform at 333 fps on an i5-8600 CPU device.
Deep Inverse Optimization
Given a set of observations generated by an optimization process, the goal of inverse optimization is to determine likely parameters of that process. We cast inverse optimization as a form of deep learning. Our method, called deep inverse optimization, is to unroll an iterative optimization process and then use backpropagation to learn parameters that generate the observations. We demonstrate that by backpropagating through the interior point algorithm we can learn the coefficients determining the cost vector and the constraints, independently or jointly, for both non-parametric and parametric linear programs, starting from one or multiple observations. With this approach, inverse optimization can leverage concepts and algorithms from deep learning.
Interpretable Deep Learning under Fire
Providing explanations for complicated deep neural network (DNN) models is critical for their usability in security-sensitive domains. A proliferation of interpretation methods have been proposed to help end users understand the inner workings of DNNs, that is, how a DNN arrives at a particular decision for a specific input. This improved interpretability is believed to offer a sense of security by involving human in the decision-making process. However, due to its data-driven nature, the interpretability itself is potentially susceptible to malicious manipulation, about which little is known thus far. In this paper, we conduct the first systematic study on the security of interpretable deep learning systems (IDLSes). We first demonstrate that existing IDLSes are highly vulnerable to adversarial manipulation. We present ACID attacks, a broad class of attacks that generate adversarial inputs which not only mislead target DNNs but also deceive their coupled interpretation models. By empirically investigating three representative types of interpretation models, we show that ACID attacks are effective against all of them. This vulnerability thus seems pervasive in many IDLSes. Further, using both analytical and empirical evidence, we identify the prediction-interpretation ‘independency’ as one possible root cause of this vulnerability: a DNN and its interpretation model are often not fully aligned, resulting in the possibility for the adversary to exploit both models simultaneously. Moreover, by examining the transferability of adversarial inputs across different interpretation models, we expose the fundamental tradeoff among the attack evasiveness with respect to different interpretation methods. These findings shed light on developing potential countermeasures and designing more robust interpretation methods, leading to several promising research directions.
Generative Adversarial Self-Imitation Learning
This paper explores a simple regularizer for reinforcement learning by proposing Generative Adversarial Self-Imitation Learning (GASIL), which encourages the agent to imitate past good trajectories via generative adversarial imitation learning framework. Instead of directly maximizing rewards, GASIL focuses on reproducing past good trajectories, which can potentially make long-term credit assignment easier when rewards are sparse and delayed. GASIL can be easily combined with any policy gradient objective by using GASIL as a learned shaped reward function. Our experimental results show that GASIL improves the performance of proximal policy optimization on 2D Point Mass and MuJoCo environments with delayed reward and stochastic dynamics.
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
Learning is an inherently continuous phenomenon. When humans learn a new task there is no explicit distinction between training and inference. After we learn a task, we keep learning about it while performing the task. What we learn and how we learn it varies during different stages of learning. Learning how to learn and adapt is a key property that enables us to generalize effortlessly to new settings. This is in contrast with conventional settings in machine learning where a trained model is frozen during inference. In this paper we study the problem of learning to learn at both training and inference time in the context of visual navigation. A fundamental challenge in navigation is generalization to unseen scenes. In this paper we propose a self-adaptive visual navigation method (SAVN) which learns to adapt to new environments without any explicit supervision. Our solution is a meta-reinforcement learning approach where an agent learns a self-supervised interaction loss that encourages effective navigation. Our experiments, performed in the AI2-THOR framework, show major improvements in both success rate and SPL for visual navigation in novel scenes.
Structure Learning Using Forced Pruning
Markov networks are widely used in many Machine Learning applications including natural language processing, computer vision, and bioinformatics . Learning Markov networks have many complications ranging from intractable computations involved to the possibility of learning a model with a huge number of parameters. In this report, we provide a computationally tractable greedy heuristic for learning Markov networks structure. The proposed heuristic results in a model with a limited predefined number of parameters. We ran our method on 3 fully-observed real datasets, and we observed that our method is doing comparably good to the state of the art methods.
A Survey on Semantic Parsing
A significant amount of information in today’s world is stored in structured and semi-structured knowledge bases. Efficient and simple methods to query these databases are essential and must not be restricted to only those who have expertise in formal query languages. The field of semantic parsing deals with converting natural language utterances to logical forms that can be easily executed on a knowledge base. In this survey, we examine the various components of a semantic parsing system and discuss prominent work ranging from the initial rule based methods to the current neural approaches to program synthesis. We also discuss methods that operate using varying levels of supervision and highlight the key challenges involved in the learning of such systems.
Deep Reinforcement Learning for Intelligent Transportation Systems
Intelligent Transportation Systems (ITSs) are envisioned to play a critical role in improving traffic flow and reducing congestion, which is a pervasive issue impacting urban areas around the globe. Rapidly advancing vehicular communication and edge cloud computation technologies provide key enablers for smart traffic management. However, operating viable real-time actuation mechanisms on a practically relevant scale involves formidable challenges, e.g., policy iteration and conventional Reinforcement Learning (RL) techniques suffer from poor scalability due to state space explosion. Motivated by these issues, we explore the potential for Deep Q-Networks (DQN) to optimize traffic light control policies. As an initial benchmark, we establish that the DQN algorithms yield the ‘thresholding’ policy in a single-intersection. Next, we examine the scalability properties of DQN algorithms and their performance in a linear network topology with several intersections along a main artery. We demonstrate that DQN algorithms produce intelligent behavior, such as the emergence of ‘greenwave’ patterns, reflecting their ability to learn favorable traffic light actuations.
Protection Against Reconstruction and Its Applications in Private Federated Learning
Federated learning has become an exciting direction for both research and practical training of models with user data. Although data remains decentralized in federated learning, it is common to assume that the model updates are sent in the clear from the devices to the server. Differential privacy has been proposed as a way to ensure the model remains private, but this does not address the issue that model updates can be seen on the server, and lead to leakage of user data. Local differential privacy is one of the strongest forms of privacy protection so that each individual’s data is privatized. However, local differential privacy, as it is traditionally used, may prove to be too stringent of a privacy condition in many high dimensional problems, such as in distributed model fitting. We propose a new paradigm for local differential privacy by providing protections against certain adversaries. Specifically, we ensure that adversaries with limited prior information cannot reconstruct, with high probability, the original data within some prescribed tolerance. This interpretation allows us to consider larger privacy parameters. We then design (optimal) DP mechanisms in this large privacy parameter regime. In this work, we combine local privacy protections along with central differential privacy to present a practical approach to do model training privately. Further, we show that these privacy restrictions maintain utility in image classification and language models that is comparable to federated learning without these privacy restrictions.
Sensitivity based Neural Networks Explanations
Although neural networks can achieve very high predictive performance on various different tasks such as image recognition or natural language processing, they are often considered as opaque ‘black boxes’. The difficulty of interpreting the predictions of a neural network often prevents its use in fields where explainability is important, such as the financial industry where regulators and auditors often insist on this aspect. In this paper, we present a way to assess the relative input features importance of a neural network based on the sensitivity of the model output with respect to its input. This method has the advantage of being fast to compute, it can provide both global and local levels of explanations and is applicable for many types of neural network architectures. We illustrate the performance of this method on both synthetic and real data and compare it with other interpretation techniques. This method is implemented into an open-source Python package that allows its users to easily generate and visualize explanations for their neural networks.
Transferring Knowledge across Learning Processes
In complex transfer learning scenarios new tasks might not be tightly linked to previous tasks. Approaches that transfer information contained only in the final parameters of a source model will therefore struggle. Instead, transfer learning at a higher level of abstraction is needed. We propose Leap, a framework that achieves this by transferring knowledge across learning processes. We associate each task with a manifold on which the training process travels from initialization to final parameters and construct a meta learning objective that minimizes the expected length of this path. Our framework leverages only information obtained during training and can be computed on the fly at negligible cost. We demonstrate that our framework outperforms competing methods, both in meta learning and transfer learning, on a set of computer vision tasks. Finally, we demonstrate that Leap can transfer knowledge across learning processes in demanding Reinforcement Learning environments (Atari) that involve millions of gradient steps.
Bach2Bach: Generating Music Using A Deep Reinforcement Learning Approach
A model of music needs to have the ability to recall past details and have a clear, coherent understanding of musical structure. Detailed in the paper is a deep reinforcement learning architecture that predicts and generates polyphonic music aligned with musical rules. The probabilistic model presented is a Bi-axial LSTM trained with a pseudo-kernel reminiscent of a convolutional kernel. To encourage exploration and impose greater global coherence on the generated music, a deep reinforcement learning approach DQN is adopted. When analyzed quantitatively and qualitatively, this approach performs well in composing polyphonic music.
A Hybrid Instance-based Transfer Learning Method
In recent years, supervised machine learning models have demonstrated tremendous success in a variety of application domains. Despite the promising results, these successful models are data hungry and their performance relies heavily on the size of training data. However, in many healthcare applications it is difficult to collect sufficiently large training datasets. Transfer learning can help overcome this issue by transferring the knowledge from readily available datasets (source) to a new dataset (target). In this work, we propose a hybrid instance-based transfer learning method that outperforms a set of baselines including state-of-the-art instance-based transfer learning approaches. Our method uses a probabilistic weighting strategy to fuse information from the source domain to the model learned in the target domain. Our method is generic, applicable to multiple source domains, and robust with respect to negative transfer. We demonstrate the effectiveness of our approach through extensive experiments for two different applications.
LEAF: A Benchmark for Federated Settings
Modern federated networks, such as those comprised of wearable devices, mobile phones, or autonomous vehicles, generate massive amounts of data each day. This wealth of data can help to learn models that can improve the user experience on each device. However, learning in federated settings presents new challenges at all stages of the machine learning pipeline. As the machine learning community begins to tackle these challenges, we are at a critical time to ensure that developments made in this area are grounded in real-world assumptions. To this end, we propose LEAF, a modular benchmarking framework for learning in federated settings. LEAF includes a suite of open-source federated datasets, a rigorous evaluation framework, and a set of reference implementations, all geared toward capturing the obstacles and intricacies of practical federated environments.
Mitigating Planner Overfitting in Model-Based Reinforcement Learning
An agent with an inaccurate model of its environment faces a difficult choice: it can ignore the errors in its model and act in the real world in whatever way it determines is optimal with respect to its model. Alternatively, it can take a more conservative stance and eschew its model in favor of optimizing its behavior solely via real-world interaction. This latter approach can be exceedingly slow to learn from experience, while the former can lead to ‘planner overfitting’ – aspects of the agent’s behavior are optimized to exploit errors in its model. This paper explores an intermediate position in which the planner seeks to avoid overfitting through a kind of regularization of the plans it considers. We present three different approaches that demonstrably mitigate planner overfitting in reinforcement-learning environments.
Unleashing the Power of Hashtags in Tweet Analytics with Distributed Framework on Apache Storm
Twitter is a popular social network platform where users can interact and post texts of up to 280 characters called tweets. Hashtags, hyperlinked words in tweets, have increasingly become crucial for tweet retrieval and search. Using hashtags for tweet topic classification is a challenging problem because of context dependent among words, slangs, abbreviation and emoticons in a short tweet along with evolving use of hashtags. Since Twitter generates millions of tweets daily, tweet analytics is a fundamental problem of Big data stream that often requires a real-time Distributed processing. This paper proposes a distributed online approach to tweet topic classification with hashtags. Being implemented on Apache Storm, a distributed real time framework, our approach incrementally identifies and updates a set of strong predictors in the Na\’ive Bayes model for classifying each incoming tweet instance. Preliminary experiments show promising results with up to 97% accuracy and 37% increase in throughput on eight processors.
Back to the Future for Dialogue Research: A Position Paper
This short position paper is intended to provide a critique of current approaches to dialogue, as well as a roadmap for collaborative dialogue research. It is unapologetically opinionated, but informed by 40 years of dialogue re-search. No attempt is made to be comprehensive. The paper will discuss current research into building so-called ‘chatbots’, slot-filling dialogue systems, and plan-based dialogue systems. For further discussion of some of these issues, please see (Allen et al., in press).
• Self-stresses control stiffness and stability in overconstrained disordered networks• Running Primal-Dual Gradient Method for Time-Varying Nonconvex Problems• Spatial-temporal Fusion Convolutional Neural Network for Simulated Driving Behavior Recognition• The Component Connectivity of Alternating Group Graphs and Split-Stars• Protection of an information system by artificial intelligence: a three-phase approach based on behaviour analysis to detect a hostile scenario• Graph calculus and the disconnected-boundary Schwinger-Dyson equations in tensor field theory• A generic coordinate descent solver for nonsmooth convex optimization• The $p$-contest with $p\ne 1$• Linear-Quadratic McKean-Vlasov Stochastic Differential Games• An improved fully nonparametric estimator of the marginal survival function based on case-control clustered data• Normal approximation of the solution to the stochastic heat equation with Lévy noise• Deep Hierarchical Machine: a Flexible Divide-and-Conquer Architecture• Proceedings of the fourth ‘international Traveling Workshop on Interactions between low-complexity data models and Sensing Techniques’ (iTWIST’18)• Towards Agent-based Models of Rumours in Organizations: A Social Practice Theory Approach• Constructions for the Elekes-Szabó and Elekes-Rónyai problems• Knowledge Distillation with Feature Maps for Image Classification• Stochastic project management: Multiple projects with multi-skilled human resources• An Interpretable Machine Vision Approach to Human Activity Recognition using Photoplethysmograph Sensor Data• Clinical Document Classification Using Labeled and Unlabeled Data Across Hospitals• Data Driven Chiller Plant Energy Optimization with Domain Knowledge• Building Sequential Inference Models for End-to-End Response Selection• Conditional gambler’s ruin problem with arbitrary winning and losing probabilities with applications• Tensor N-tubal rank and its convex relaxation for low-rank tensor recovery• Total 2-domination of proper interval graphs• Absorption time and absorption probabilities for a family of multidimensional gambler models• An Analysis by Synthesis Approach for Automatic Vertebral Shape Identification in Clinical QCT• Predicting Blood Pressure Response to Fluid Bolus Therapy Using Attention-Based Neural Networks for Clinical Interpretability• Fast Nonlinear Fourier Transform Algorithms Using Higher Order Exponential Integrators• Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networks• Care2Vec: A Deep learning approach for the classification of self-care problems in physically disabled children• Enhancing Perceptual Attributes with Bayesian Style Generation• On functional logistic regression via RKHS’s• SUSiNet: See, Understand and Summarize it• Towards Accurate Task Accomplishment with Low-Cost Robotic Arms• Averaging Principle and Shape Theorem for a Growth Model with Memory• Projections of Poisson cut-outs in the Heisenberg group and the visual $3$-sphere• Attention-based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions• Market Integration of HVDC Lines• Nose, eyes and ears: Head pose estimation by locating facial keypoints• Disentangling Adversarial Robustness and Generalization• Wireless Communications and Control for Swarms of Cellular-Connected UAVs• Regularity and Stability of Invariant Measures for Diffusion Processes under Synthetic Lower Ricci Curvature Bounds• Effects of forecast errors on optimal utilisation in aggregate production planning with stochastic customer demand• Kinetically Constrained Models with Random Constraints• Double shuffle relations for arborified zeta values• Malware static analysis and DDoS capabilities detection• The RGNLP Machine Translation Systems for WAT 2018• Towards Spectral Estimation from a Single RGB Image in the Wild• A Wasserstein GAN model with the total variational regularization• Comparing Neural- and N-Gram-Based Language Models for Word Segmentation• Fisher-Shannon complexity analysis of high-frequency urban wind speed time series• Novel Quality Metric for Duration Variability Compensation in Speaker Verification using i-Vectors• Planar Ramsey graphs• Locally Recoverable codes with local error detection• Exit times for semimartingales under nonlinear expectation• Early Prediction of Course Grades: Models and Feature Selection• FDD Channel Estimation via Covariance Identification in Wideband Massive MIMO Systems• Delay constrained Energy Optimization for Edge Cloud Offloading• On the Power of Preprocessing in Decentralized Network Optimization• Towards Solving Text-based Games by Producing Adaptive Action Spaces• Thompson Sampling for Noncompliant Bandits• Coalescences in Continuous-State Branching Processes• Iterative Potts minimization for the recovery of signals with discontinuities from indirect measurements — the multivariate case• Collision-Free Multi Robot Trajectory Optimization in Unknown Environments using Decentralized Trajectory Planning• Lines of descent in the deterministic mutation-selection model with pairwise interaction• AsyncQVI: Asynchronous-Parallel Q-Value Iteration for Reinforcement Learning with Near-Optimal Sample Complexity• What can I do here? Leveraging Deep 3D saliency and geometry for fast and scalable multiple affordance detection• Domain Alignment with Triplets• Divergence of predictive model output as indication of phase transitions• A Coalition-Based Communication Framework for Intelligent Flying Ad-Hoc Networks• Generating Diverse Programs with Instruction Conditioned Reinforced Adversarial Learning• Toward Scalable Neural Dialogue State Tracking Model• On Closest Pair in Euclidean Metric: Monochromatic is as Hard as Bichromatic• The CEO Problem with $r$th Power of Difference and Logarithmic Distortions• Efficient Distributed-Memory Parallel Matrix-Vector Multiplication with Wide or Tall Unstructured Sparse Matrices• Generalised Approximate Message Passing for Non-I.I.D. Sparse Signals• Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attacks• From the User to the Medium: Neural Profiling Across Web Communities• The Right (Angled) Perspective: Improving the Understanding of Road Scenes using Boosted Inverse Perspective Mapping• Accelerating Large Scale Knowledge Distillation via Dynamic Importance Sampling• Hollow polytopes of large width• Multi-agent Deep Reinforcement Learning with Extremely Noisy Observations• Analysis of Geometric Selection of the Data-Error Covariance Inflation for ES-MDA• SPLAT: Semantic Pixel-Level Adaptation Transforms for Detection• Differentially Private Obfuscation Mechanisms for Hiding Probability Distributions• Visual Memory for Robust Path Following• On Berinde’s method for comparing iterative processes• A Longitudinal Analysis of the Public Perception of the Opportunities and Challenges of the Internet of Things• Avoiding patterns and making the best choice• Chest X-Rays Image Inpainting with Context Encoders• Analysing the Robustness of Evolutionary Algorithms to Noise: Refined Runtime Bounds and an Example Where Noise is Beneficial• FoldingZero: Protein Folding from Scratch in Hydrophobic-Polar Model• Online Graph-Adaptive Learning with Scalability and Privacy• Timely Updates in Energy Harvesting Two-hop Networks: Offline and Online Policies• On Mixed Domination in Generalized Petersen Graphs• DeepVoxels: Learning Persistent 3D Feature Embeddings• Automatically Annotating Articles Towards Opening and Reusing Transparent Peer Reviews• Designing quantum experiments with a genetic algorithm• A Two-Stream Variational Adversarial Network for Video Generation• Quantum Approximate Optimization Algorithm: Performance, Mechanism, and Implementation on Near-Term Devices• Identification and Recognition of Rice Diseases and Pests Using Deep Convolutional Neural Networks• The formula for Turán number of spanning linear forests• Brain Tumor Segmentation using an Ensemble of 3D U-Nets and Overall Survival Prediction using Radiomic Features• Disentangling Latent Hands for Image Synthesis and Pose Estimation• MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language• Strong Existence and Uniqueness of Diffusions with local time dependent noise• Symbolic Approximation of Weighted Timed Games• QR code denoising using parallel Hopfield networks• Machine Friendly Machine Learning: Interpretation of Computed Tomography Without Image Reconstruction• Learning Multimodal Graph-to-Graph Translation for Molecular Optimization• Semantic Image Inpainting Through Improved Wasserstein Generative Adversarial Networks• Distilling Information from a Flood: A Possibility for the Use of Meta-Analysis and Systematic Review in Machine Learning Research• Brief survey of Mobility Analyses based on Mobile Phone Datasets• Crowd Sourcing based Active Learning Approach for Parking Sign Recognition• ZerNet: Convolutional Neural Networks on Arbitrary Surfaces via Zernike Local Tangent Space Estimation• A System for Automated Image Editing from Natural Language Commands• Disease Detection in Weakly Annotated Volumetric Medical Images using a Convolutional LSTM Network• Concentration inequalities for bounded functionals via generalized log-Sobolev inequalities• A Single Time-Scale Stochastic Approximation Method for Nested Stochastic Optimization• Exploring galaxy evolution with generative models• On learning with shift-invariant structures• Tracking Sparse mmWave Channel under Time Varying Multipath Scatterers• ORACLE: Optimized Radio clAssification through Convolutional neuraL nEtworks• Wideband Full-Duplex Wireless via Frequency-Domain Equalization: Design and Experimentation• Learning to Predict Ego-Vehicle Poses for Sampling-Based Nonholonomic Motion Planning• A Unified Approach to Dynamic Decision Problems with Asymmetric Information – Part I: Non-Strategic Agents• A Unified Approach to Dynamic Decision Problems with Asymmetric Information – Part II: Strategic Agents• Sequential Experiment Design for Hypothesis Verification• Determinant Codes with Helper-Independent Repair for Single and Multiple Failures• Boundary Vibration Control of Strain Gradient Timoshenko Micro-Cantilevers Using Piezoelectric Actuators• Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics• A Spectral Regularizer for Unsupervised Disentanglement• Hierarchical Continuous Time Hidden Markov Model, with Application in Zero-Inflated Accelerometer Data• Sum of squares bounds for the total ordering principle• Pre-Defined Sparse Neural Networks with Hardware Acceleration• $Δ$-Algebra and Scattering Amplitudes• On incompressible high order networks• Test of Covariance and Correlation Matrices• Some manifold learning considerations towards explicit model predictive control
Like this:
Like Loading…
Related