Related papers: Stochastic Configuration Machines: FPGA Implementa…

In this paper, a spintronic neuromorphic reconfigurable Array (SNRA) is developed to fuse together power-efficient probabilistic and in-field programmable deterministic computing during both training and evaluation phases of restricted…

The Restricted Boltzmann Machine (RBM) is a stochastic neural network capable of solving a variety of difficult tasks such as NP-Hard combinatorial optimization problems and integer factorization. The RBM architecture is also very compact;…

We introduce factorize sum split product networks (FSPNs), a new class of probabilistic graphical models (PGMs). FSPNs are designed to overcome the drawbacks of existing PGMs in terms of estimation accuracy and inference efficiency.…

Many approaches to transform classification problems from non-linear to linear by feature transformation have been recently presented in the literature. These notably include sparse coding methods and deep neural networks. However, many of…

Matched filters are widely used to localise signal patterns due to their high efficiency and interpretability. However, their effectiveness deteriorates for low signal-to-noise ratio (SNR) signals, such as those recorded on edge devices,…

The emergence of deep and large-scale spiking neural networks (SNNs) exhibiting high performance across diverse complex datasets has led to a need for compressing network models due to the presence of a significant number of redundant…

We study the typical learning properties of the recently introduced Soft Margin Classifiers (SMCs), learning realizable and unrealizable tasks, with the tools of Statistical Mechanics. We derive analytically the behaviour of the learning…

The hardware implementation of deep neural networks (DNNs) has recently received tremendous attention: many applications in fact require high-speed operations that suit a hardware implementation. However, numerous elements and complex…

Variety of machine learning problems can be formulated as an optimization task for some (surrogate) loss function. Calculation of loss function can be viewed in terms of stochastic computation graphs (SCG). We use this formalism to analyze…

Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication overhead. We introduce STEM (Scaling Transformers with…

Industrial forecasting often involves multi-source asynchronous signals and multi-output targets, while deployment requires explicit trade-offs between prediction error and model complexity. Current practices typically fix alignment…

It is a challenging task to deploy computationally and memory intensive State-of-the-art deep neural networks (DNNs) on embedded systems with limited hardware resources and power budgets. Recently developed techniques like Deep Compression…

Deep Neural Networks (DNNs) have achieved extraordinary performance in various application domains. To support diverse DNN models, efficient implementations of DNN inference on edge-computing platforms, e.g., ASICs, FPGAs, and embedded…

Recurrent Neural Networks and in particular Long Short-Term Memory (LSTM) networks have demonstrated state-of-the-art accuracy in several emerging Artificial Intelligence tasks. However, the models are becoming increasingly demanding in…

In this work, we propose a new approach towards the efficient optimization and implementation of reservoir computing hardware reducing the required domain expert knowledge and optimization effort. First, we adapt the reservoir input mask to…

Intensive computation is entering data centers with multiple workloads of deep learning. To balance the compute efficiency, performance, and total cost of ownership (TCO), the use of a field-programmable gate array (FPGA) with…

The representation of functions by artificial neural networks depends on a large number of parameters in a non-linear fashion. Suitable parameters of these are found by minimizing a 'loss functional', typically by stochastic gradient…

While the machine learning literature dedicated to fully automated reasoning algorithms is abundant, the number of methods enabling the inference process on the basis of previously defined knowledge structures is scanter. Fuzzy Cognitive…

Spiking Neural Networks (SNNs) offer high energy efficiency and event-driven computation, ideal for low-power edge AI. Their hardware implementation on FPGAs, however, faces challenges due to heavy computation, large memory use, and limited…

Stochastic block models (SBMs) are often used to find assortative community structures in networks, such that the probability of connections within communities is higher than in between communities. However, classic SBMs are not limited to…