A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
V-HMN integrates memory mechanisms for improved image recognition.
Prototype-based generative replay framework for online continual regression.
Prototype-based memory network learns visual categories from unlabeled data.
Neural networks currently dominate the machine learning community and they do so for good reasons. Their accuracy on complex tasks such as image classification is unrivaled at the moment and with recent improvements they are reasonably easy to train. Nevertheless, neural networks are lacking robustness and interpretabi…
We present a modelling framework for the investigation of prototype-based classifiers in non-stationary environments. Specifically, we study Learning Vector Quantization (LVQ) systems trained from a stream of high-dimensional, clustered data.We consider standard winner-takes-all updates known as LVQ1. Statistical prope…
A new method improves quantile regression for high-dimensional data.
ProtoX-AD: A self-explainable time series anomaly detection framework
TPM improves medical image segmentation by separating foreground and background.
IMKPL learns interpretable prototypes for better classification.
ProtoryNet interprets text sequences using prototype trajectories for better understanding.
In this paper we formulate in general terms an approach to prove strong consistency of the Empirical Risk Minimisation inductive principle applied to the prototype or distance based clustering. This approach was motivated by the Divisive Information-Theoretic Feature Clustering model in probabilistic space with Kullbac…
An appropriate choice of the activation function (like ReLU, sigmoid or swish) plays an important role in the performance of (deep) multilayer perceptrons (MLP) for classification and regression learning. Prototype-based classification learning methods like (generalized) learning vector quantization (GLVQ) are powerful…
We propose in this contribution a method for l one regularization in prototype based relevance learning vector quantization (LVQ) for sparse relevance profiles. Sparse relevance profiles in hyperspectral data analysis fade down those spectral bands which are not necessary for classification. In particular, we consider …
The increasing use of machine learning in practice and legal regulations like EU's GDPR cause the necessity to be able to explain the prediction and behavior of machine learning models. A prominent example of particularly intuitive explanations of AI models in the context of decision making are counterfactual explanati…
Meta-learning extracts common knowledge from learning different tasks and uses it for unseen tasks. It can significantly improve tasks that suffer from insufficient training data, e.g., few shot learning. In most meta-learning methods, tasks are implicitly related by sharing parameters or optimizer. In this paper, we s…
A new neural network method improves interpretability and detection of outliers.
In this paper, a similarity-driven cluster merging method is proposed for unsuper-vised fuzzy clustering. The cluster merging method is used to resolve the problem of cluster validation. Starting with an overspecified number of clusters in the data, pairs of similar clusters are merged based on the proposed similarity-…
New fair-by-design model reduces bias in recidivism prediction.
Paper tackles graph class-incremental learning with task profiling and prompting.
Designing a new drug is a lengthy and expensive process. As the space of potential molecules is very large (10^23-10^60), a common technique during drug discovery is to start from a molecule which already has some of the desired properties. An interdisciplinary team of scientists generates hypothesis about the required…
The paper proposes a method to predict the performance of data-driven algorithms using surrogate models.
New algorithm detects and adapts to changes in real-time data streams.
In this paper we propose a simple yet powerful method for learning representations in supervised learning scenarios where each original input datapoint is described by a set of vectors and their associated outputs may be given by soft labels indicating, for example, class probabilities. We represent an input datapoint …
Paper proposes integrating hierarchical class structure into prototypical network supervision.
Proposes a novel SAM operator for separate item and relational memories.
Geometric framework links clustering accuracy to structural recovery.
In this paper, we propose a dual memory structure for reinforcement learning algorithms with replay memory. The dual memory consists of a main memory that stores various data and a cache memory that manages the data and trains the reinforcement learning agent efficiently. Experimental results show that the dual memory …
UniShape improves time series classification by selecting relevant subsequences.
Stable Hadamard Memory improves reinforcement learning by efficiently managing memory.
New memory allocation scheme improves image generation performance.
DAM with MRL improves relational reasoning in MANNs.
We discuss memory models which are based on tensor decompositions using latent representations of entities and events. We show how episodic memory and semantic memory can be realized and discuss how new memory traces can be generated from sensory input: Existing memories are the basis for perception and new memories ar…
mGRN improves multivariate time series prediction by managing marginal and joint memories.
Model combines long-term and short-term memory using conceptors.
Learning to remember long sequences remains a challenging task for recurrent neural networks. Register memory and attention mechanisms were both proposed to resolve the issue with either high computational cost to retain memory differentiability, or by discounting the RNN representation learning towards encoding shorte…
In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks. However, previous MANNs suffer from complex memory addressing mechanism, making them relatively hard to train and causing computational overheads. Moreove…
Enhanced Hopfield model boosts memory retrieval capacity.
Current generation of memory-augmented neural networks has limited scalability as they cannot efficiently process data that are too large to fit in the external memory storage. One example of this is lifelong learning scenario where the model receives unlimited length of data stream as an input which contains vast majo…
Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which …
Memory-constrained algorithms need superlinear memory for efficient convex optimization.
We present an end-to-end trained memory system that quickly adapts to new data and generates samples like them. Inspired by Kanerva's sparse distributed memory, it has a robust distributed reading and writing mechanism. The memory is analytically tractable, which enables optimal on-line compression via a Bayesian updat…
Generative diffusion models mimic biological memory networks, encoding associative dynamics in deep neural weights.
A new model for sequential memory using temporal predictive coding.
We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning. We conceptualize this memory as a rapidly adaptable function that we parameterize as a deep neural network. Reading from the neural memory function amounts to pushing an input (the key vector) throug…
A new memory system handles non-stationary environments by self-sizing and retaining memories.
Accelerators with power-law memory are proposed in the framework of the discrete time approach. To describe discrete accelerators we use the capital stock adjustment principle, which has been suggested by Matthews.The suggested discrete accelerators with memory describe the economic processes with the power-law memory …
Paper questions RNN and LSTM's long-term memory and introduces a new definition.
Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular challenge for deep learning. In this regard, various researches on "meta-learning…