Neural Programmer learns natural language queries for databases.
problem Natural language interface learning for database queries.
method Enhanced Neural Programmer model trained on weak supervision.
result Single Neural Programmer model achieves 34.2% accuracy.
Deep neural networks have achieved impressive supervised classification performance in many tasks including image recognition, speech recognition, and sequence to sequence learning. However, this success has not been translated to applications like question answering that may involve complex arithmetic and logic reason…
Condensa programmatically optimizes neural network compression.
problem Finding optimal compression strategies for neural networks.
method Bayesian optimization-based algorithm for automatic sparsity inference.
result Significant memory and runtime improvements for real-world DNNs.
FixyNN improves energy efficiency of mobile computer vision tasks.
problem High energy consumption of state-of-the-art CNN models on mobile devices.
method Fixed-weight feature extractor and programmable CNN accelerator for transfer learning.
result Achieved up to 26.6 TOPS/W energy efficiency, nearly 2x more efficient than conventional accelerators.
Paper reduces AI complexity with pre-defined sparsity and hardware acceleration.
problem Reduction of computational and storage complexity in neural networks.
method Pre-defined sparsity and hardware acceleration architecture.
result Significant reduction in storage and computational complexity (5X+ reduction) without significant performance loss.
Study evaluates training programs for unemployed in Belgium using machine learning.
problem Determining which training programs are most effective for unemployed individuals in Belgium.
method Used Modified Causal Forests, a causal machine learning estimator, to analyze data from unemployed in Belgium.
result There is significant heterogeneity in the effectiveness of different training programs for unemployed individuals in Belgium.
Researchers show NN-based communication algorithms can be implemented on hardware without significant performance loss.
problem Reducing complexity and improving performance of NN-based communication algorithms for practical hardware implementation.
method Implementation of NN-based algorithms in fixed-point arithmetic with quantized weights on specialized hardware (FPGAs, ASICs).
result It is possible to implement NN-based algorithms in fixed-point arithmetic with quantized weights on hardware without significant performance loss.
Graph neural networks improve charged particle tracking on FPGAs.
problem Charged particle trajectory determination in high interaction density conditions.
method Graph neural networks (GNNs) embedded in tracker data as graphs, classifying edges as track segments.
result GNNs implemented on FPGAs for charged particle tracking, enabling future HL-LHC experiments.
A fast method for learning MZI parameters in optical neural networks.
problem Time-consuming learning of MZI parameters in optical neural networks.
method Customized complex-valued derivatives and a chain rule for Wirtinger derivatives, incorporated into a function module.
result 20 times faster learning compared to conventional AD in MNIST task.
New method forecasts workforce reintegration success rates.
problem Estimating success of reskilling programs in changing labor markets.
method Uses current workforce demand and supply factors, not historical data.
result Average error of 3.9% compared to 5.4% for best benchmark.
In this paper we propose a Bayesian nonparametric model for clustering partial ranking data. We start by developing a Bayesian nonparametric extension of the popular Plackett-Luce choice model that can handle an infinite number of choice items. Our framework is based on the theory of random atomic measures, with the pr…
dYdX updates liquidity provider incentives to enhance trading efficiency.
problem Incentivizing liquidity providers to maintain efficient market structures.
method Analyzed various metrics (makerVolume, depths, spreads) and used historical trades to update the LP Incentives Programme.
result Updated the LP Incentives Programme to encourage more active and efficient liquidity.
Develops inference combinators for probabilistic programs using neural networks.
problem Creating efficient proposals for probabilistic program inference.
method Inference combinators using neural network parameterization of proposals.
result Correct by construction variational methods tailored to specific models.
This paper completes a programme to determine which toric surfaces admit Kahler metrics of constant scalar curvature/
New networks interpret kernel decompositions for signal analysis.
problem Mode decomposition in signal analysis.
method Programmable and interpretable regression networks using kernels and data.
result Near machine precision recovery of signal modes under regularity and separation assumptions.
A hardware-based reservoir computing system predicts time series with high speed and accuracy.
problem Processing time-dependent signals with high speed and accuracy.
method A hardware-based reservoir computing system using a field-programmable gate array (FPGA) for both the reservoir and output layers.
result Achieves comparable accuracy to software approaches but with a superior real-time prediction rate up to 160 MHz.
Paper presents FPGA implementation for efficient recurrent neural networks.
problem Implementing recurrent neural networks on FPGAs for low latency.
method Developed hls4ml framework to implement LSTM and GRU layers.
result Demonstrated effective designs for both small and large models.
Vanlearning simplifies machine learning for non-programmers.
problem Limited accessibility of machine learning tools for non-programmers.
method SaaS application with user-friendly interface and data pre-processor.
result Users can analyze data without coding or machine learning knowledge.
SED integrates synthesis, execution, and debugging for neural program synthesis.
problem Challenges in synthesizing complex programs that match specifications.
method SED combines synthesis, execution, and debugging to improve neural program generation.
result SED reduces error rates and outperforms standard decoding methods.
Study forecasts food security trends using real-time data.
problem Food insecurity prediction for sub-national regions.
method Quantitative methodology combining various machine learning models.
result Reservoir Computing model performs best in food security prediction.
We outline a framework which generalizes Felix Klein's Erlanger Programm which he announced in 1872 after exchanging ideas with Sophus Lie.
The paper gives a review of progress towards extending the Thurston programme to the Poincare duality case. For a full abstract, see the published version at the above link.
Accelerator boosts energy efficiency for MANNs on FPGAs.
problem Efficiently running MANNs on accelerators designed for other NNs.
method Data flow architecture, inference thresholding.
result Higher energy efficiency compared to NVIDIA GPU.
FixyNN splits CNN models into fixed and trainable parts for efficient on-device inference.
problem Energy inefficiency in on-device CNN inference for real-time computer vision.
method Co-designed hardware accelerator platform with transfer learning for training.
result Achieved nearly 2x better energy efficiency than a conventional accelerator.
System builds Somali ASR for UN humanitarian efforts.
problem Developing ASR for under-resourced Somali language.
method Acoustic model training with annotated speech, neural architectures, language model data augmentation, acoustic data perturbation.
result Best system achieved 53.75% word error rate.
This study categorizes RWA tokenization challenges and solutions.
problem Navigating the gap between on-chain deterministic code and off-chain probabilistic reality.
method Taxonomy and comparative analysis of RWA protocols, legal and technical standards.
result RWA tokenization requires overcoming legal and technical interoperability issues.
Graph Neural Networks align with dynamic programming, improving algorithmic reasoning.
problem Demonstrate and quantify alignment between GNNs and dynamic programming.
method Category theory and abstract algebra methods to expose intricate connection.
result Showed GNNs align with dynamic programming beyond individual algorithms.
New methods estimate heterogeneous causal effects at various levels.
problem Estimating causal effects at different levels of granularity.
method Modified Causal Forests approach for multiple treatment models.
result New estimators outperform existing methods in empirical studies.
PDSketch enables flexible robot planning by learning from domain structures.
problem Building general robots with flexible planning.
method Exploiting locality and sparsity in environmental models, PDSketch defines high-level structures for trainable neural networks.
result PDSketch automatically generates planning heuristics without additional training.
Study optimizes CT and microinsurance for efficient social protection in low-income countries.
problem Efficient targeting of cash transfers to reduce social protection costs in low-income countries.
method Modelled household capital dynamics using piecewise-deterministic Markov process, derived HJB equation for optimal injection, used dynamic programming.
result Optimal level of capital injection above poverty threshold for cost-effective social protection.
We give some detailed numerical information about extremal metrics on four different toric surfaces. These are sample of many other cases which can be treated using a computer programme outlined in the paper.
We discuss of the conceptual difficulties connected with the anticommutativity of classical fermion fields, and we argue that the "space" of all classical configurations of a model with such fields should be described as an infinite-dimensional supermanifold M. We discuss the two main approaches to supermanifolds, and …
Generative neural nets learn deep policies conditioned on goals.
problem Learning optimal policies for specific goals in reinforcement learning.
method Goal-conditioned neural nets that generate deep neural policies.
result Single learned policy generator can achieve any desired return.
Jointly learning to localize and repair variable-misuse bugs improves program repair.
problem Variable-misuse bugs in programs.
method Multi-headed pointer networks for joint localization and repair.
result Joint model significantly outperforms an enumerative solution.
New approach uses Boolean circuits to optimize neural networks.
problem Improving efficiency of neural network implementations on hardware accelerators.
method Formalized neural networks as Boolean circuits, showing binarized networks are functionally complete.
result Binarized neural networks are functionally complete, suggesting new possibilities for neural network accelerators.
In this study, after introducing algebraic properties of real quaternions some characterizations of quaternionic involute-evolute curves in Q are obtained. And some results and theorems for quaternionic w-curves are given. Lastly, we illustrate some examples and draw their figures with Mathematica Programme.
Transformers can emulate various algorithms by prompting, proving universality.
problem How to emulate algorithms using fixed-weight Transformers.
method Two modes of in-context algorithm emulation: task-specific and prompt-programmable. Constructing prompts that encode algorithm parameters into token representations.
result Fixed-weight Transformers can emulate a broad class of algorithms via prompts.
LeFlow enables quick FPGA synthesis from Tensorflow models.
problem Manual translation of Tensorflow models to FPGA RTL is time-consuming and requires expertise.
method Uses XLA compiler to emit synthesizable LLVM code from Tensorflow specifications, which is then synthesized.
result Allows users to generate Deep Neural Networks with just a few lines of Python code.
AquaSight detects water impurity using deep learning.
problem Water pollution and lack of affordable water quality assessment.
method Convolutional Neural Networks for automated water impurity detection.
result Deep learning model achieved 96% accuracy in detecting water contamination.
In these expository notes we draw together and develop the ideas behind some recent progress in two directions: the treatment of finite type partial differential operators by prolongation, and a class of differential complexes known as detour complexes. This elaborates on a lecture given at the IMA Summer Programme ``S…
This paper attempts to relate some ideas of Grothendieck in his Esquisse d'un programme and some of the recent results on 2-dimensional topology and geometry. Especially, we shall discuss the Teichmüller theory, the mapping class groups, SL(2,C) representation variety of surface groups, and Thurston's theory o…
Efficient FPGA dropout algorithm reduces memory usage.
problem Overfitting in deep neural networks.
method Hardware-oriented dropout algorithm for FPGA implementation.
result Significant resource reduction in FPGA implementation.
This thesis constructs mirrors for D-branes in toric Calabi-Yau manifolds.
problem Constructing mirrors for D-branes in complex algebraic varieties.
method SYZ programme techniques, including modifications for open Gromov-Witten invariants.
result Explicit mirror construction for Aganagic-Vafa A-branes with quantum correction.
We study on a new kind of surface covered by translation and factorable (TF-type) surfaces in the three dimensional Euclidean space. We consider I and III Laplace-Beltrami operator surfaces of a TF-type surface. Then we obtain degrees and classes of algebraic surfaces of the surfaces using eliminate methods on software…
This paper proposes a new way to quantize classical mechanical systems. Here we use ALAG - programme to construct moduli space of half weighted Bohr - Sommerfeld lagrangian cycles of fixed volume which is our quantum phase space. "Dynamical correspondence" principle makes possible to prove that this ALAG - quantization…
PoET-BiN reduces power consumption in neural networks on embedded devices.
problem Power inefficiency in neural network implementations on embedded platforms.
method Look-Up Table based implementation with a modified Decision Tree approach.
result Near state-of-the-art results with up to 6 orders of magnitude energy reduction.
PolyLUT uses polynomials to reduce FPGA latency.
problem Reducing latency in FPGA-based neural network inference.
method Training neural networks using multivariate polynomials as basic building blocks.
result Achieved significant latency and area improvements.
New rational curvature measures for 2-complexes.
problem Measuring curvature in 2-dimensional cell complexes.
method Defined and proved rational curvature invariants.
result Computable rational curvature bounds for 2-complexes.