Anthony S. Maida

University of Louisiana at Lafayette | ULL · The Centre for Advanced Computer Studies

Since the onset of LLMs, translating natural language queries to structured SQL commands is assuming increasing. Unlike the previous reviews, this survey provides a comprehensive study of the evolution of LLM-based text-to-SQL systems, from early rule-based models to advanced LLM approaches, and how LLMs impacted this field. We discuss benchmarks,...

In recent years,Hypercomplex-inspired neural networks improved deep CNN architectures due to their ability to share weights across input channels and thus improve cohesivenessof representations within the layers.The work described herein studies the effect of replacing existing layers inan Axial Attention ResNet with their quaternion variants that...

The most common eye infection in people with diabetes is diabetic retinopathy (DR). It might cause blurred vision or even total blindness. Therefore, it is essential to promote early detection to prevent or alleviate the impact of DR. However, due to the possibility that symptoms may not be noticeable in the early stages of DR, it is difficult for...

Deep hypercomplex-inspired convolutional neural networks (CNNs) have recently enhanced feature extraction for image classification by allowing weight sharing across input channels. This makes it possible to improve the representation acquisition abilities of the networks. Hypercomplex-inspired networks, however, still incur higher computational cos...

Recently, many deep networks have introduced hypercomplex and related calculations into their architectures. In regard to convolutional networks for classification, these enhancements have been applied to the convolution operations in the frontend to enhance accuracy and/or reduce the parameter requirements while maintaining accuracy. Although thes...

Over the past decade, deep hypercomplex-inspired networks have enhanced feature extraction for image classification by enabling weight sharing across input channels. Recent works make it possible to improve representational capabilities by using hypercomplex-inspired networks which consume high computational costs. This paper reduces this cost by f...

While residual networks (ResNets) demonstrate outstanding performance on computer vision tasks, their computational cost still remains high. Here, we focus on reducing this cost by proposing a new network architecture, axial ResNet, which replaces spatial 2D convolution operations with two consecutive 1D convolution operations. Convergence of very...

Long short-term memory (LSTM) is one of the robust recurrent neural network architectures for learning sequential data. However, it requires considerable computational power to learn and implement both software and hardware aspects. This paper proposed a novel LiteLSTM architecture based on reducing the LSTM computation components via the weights s...

Diabetic Retinopathy (DR), the most prevalent eye condition in diabetic patients, can be brought on by diabetes. It may result in reduced eyesight or possibly complete blindness. Early detection can help prevent eye damage, but it can be challenging because symptoms might not show up right away. To grade diabetic retinopathy and identify all stages...

Video frame prediction is needed for various computer-vision-based systems such as self-driving vehicles and video streaming. This paper proposes a novel Inception-based convolutional recurrent neural network (RNN) as an enhancement to a basic gated convolutional RNN. A basic gated convolutional RNN has fixed-size kernels that are hyperparameters o...

Hearing-impaired is the disability of partial or total hearing loss that causes a significant problem for communication with other people in society. American Sign Language (ASL) is one of the sign languages that most commonly used language used by Hearing impaired communities to communicate with each other. In this paper, we proposed a simple deep...

Recent theoretical and experimental works have connected Hebbian plasticity with the reinforcement learning (RL) paradigm, producing a class of trial-and-error learning in artificial neural networks known as neo-Hebbian plasticity. Inspired by the role of the neuromodulator dopamine in synaptic modification, neo-Hebbian RL methods extend unsupervis...

Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware aspects. This paper proposes a novel LiteLSTM architecture based on reducing the computation components of the...

p>1. We developed a novel predictive model based on Efficient Net b3 pre-trained Convolutional Neural Network for reliable classification of Diabetic Retinopathy into 5 Stages, namely: 0 – No DR, 1 – Mild DR, 2 – Moderate DR, 3 – Severe DR, 4 – Proliferate DR. These 5 stages are based on the severity of diabetic retinopathy. Since treatment varies...

p>1. We developed a novel predictive model based on Efficient Net b3 pre-trained Convolutional Neural Network for reliable classification of Diabetic Retinopathy into 5 Stages, namely: 0 – No DR, 1 – Mild DR, 2 – Moderate DR, 3 – Severe DR, 4 – Proliferate DR. These 5 stages are based on the severity of diabetic retinopathy. Since treatment varies...

We study the effectiveness of attention augmented convolutional neural networks for musical instrument identification in audio, which is an unsolved problem. Attention augmentation has not previously been applied to this task. The proposed architecture augments the final convolution modules from a baseline convolutional template with attention mech...

Background Blood glucose (BG) management is crucial for type-1 diabetes patients resulting in the necessity of reliable artificial pancreas or insulin infusion systems. In recent years, deep learning techniques have been utilized for a more accurate BG level prediction system. However, continuous glucose monitoring (CGM) readings are susceptible to...

Blood glucose (BG) management is crucial for type-1 diabetes patients resulting in the necessity of reliable artificial pancreas or insulin infusion systems. In recent years, deep learning techniques have been utilized for a more accurate BG level prediction system. However, continuous glucose monitoring (CGM) readings are susceptible to sensor err...

We show that the core reasons that complex and hypercomplex valued neural networks offer improvements over their real-valued counterparts is the weight sharing mechanism and treating multidimensional data as a single entity. Their algebra linearly combines the dimensions, making each dimension related to the others. However, both are constrained to...

Power grid operators rely on solar irradiance forecasts to manage uncertainty and variability associated with solar power. Meteorological factors such as cloud cover, wind direction, and wind speed affect irradiance and are associated with a high degree of variability and uncertainty. Statistical models fail to accurately capture the dependence bet...

Bayesian predictive coding is a putative neuromorphic method for acquiring higher-level neural representations to account for sensory input. Although originating in the neuroscience community, there are also efforts in the machine learning community to study these models. This paper reviews some of the more well known models. Our review analyzes mo...

In this paper, we proposed a novel deep-learning method called Inception LSTM for video frame prediction. A standard convolutional LSTM uses a single size kernel for each of its gates. Having multiple kernel sizes within a single gate would provide a richer features that would otherwise not be possible with a single kernel. Our key idea is to intro...

Spatiotemporal sequence prediction is an important problem in deep learning. We study next‐frame(s) video prediction using a deep‐learning‐based predictive coding framework that uses convolutional LSTM (convLSTM) modules. We introduce a novel rgcLSTM architecture that requires a significantly lower parameter budget than a comparable convLSTM. By us...

In this paper, we proposed a novel deep-learning method called Inception LSTM for video frame prediction. A standard convolutional LSTM uses a single size kernel for each of its gates. Having multiple kernel sizes within a single gate would provide a richer features that would otherwise not be possible with a single kernel. Our key idea is to intro...

The problem of video frame prediction has received much interest due to its relevance to many computer vision applications such as autonomous vehicles or robotics. Supervised methods for video frame prediction rely on labeled data, which may not always be available. In this paper, we provide a novel unsupervised deep-learning method called Inceptio...

Convolutional LSTMs are widely used for spatiotemporal prediction. We study the effect of using different activation functions for two types of units within convolutional LSTM modules, namely gate units and non-gate units. The research provides guidance for choosing the best activation function to use in convolutional LSTMs for video prediction. Mo...

Hybrid LSTM-fully convolutional networks (LSTM-FCN) for time series classification have produced state-of-the-art classification results on univariate time series. We show that replacing the LSTM with a gated recurrent unit (GRU) to create a GRU-fully convolutional network hybrid model (GRU-FCN) can offer even better performance on many time series...

We provide data-driven machine learning methods that are capable of making real-time influenza forecasts that integrate the impacts of climatic factors and geographical proximity to achieve better forecasting performance. The key contributions of our approach are both applying deep learning methods and incorporation of environmental and spatio-temp...

The problem of training spiking neural networks (SNNs) is a necessary precondition to understanding computations within the brain, a field still in its infancy. Previous work has shown that supervised learning in multi-layer SNNs enables bio-inspired networks to recognize patterns of stimuli through hierarchical feature acquisition. Although gradie...

Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame(s) video prediction using a deep-learning-based predictive coding framework that uses convolutional, long short-term memory (convLSTM) modules. We introduce a novel reduced-gate convolutional LSTM (rgcLSTM) architecture that requires a significantly low...

We present a novel adaptive feedforward neural network for online learning from doubly-streaming data, where both the data volume and feature space grow simultaneously. Traditional online learning and feature selection algorithms can’t handle this problem because they assume that the feature space of the data stream remains unchanged. We propose a...

Although representation learning methods developed within the framework of traditional neural networks are relatively mature, developing a spiking representation model remains a challenging problem. This paper proposes an event-based method to train a feedforward spiking neural network (SNN) layer for extracting visual features. The method introduc...

In recent years, deep learning has been a revolution in the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained in a supervised manner using backpropagation. Huge amounts of labeled examples are required, but the resulting classification accuracy is truly imp...

"The final publication is available at Springer via http://dx.doi.org/10.1007/s11265-016-1153-2" It is of some interest to understand how statistically based mechanisms for signal processing might be integrated with biologically motivated mechanisms such as neural networks. This paper explores a novel hybrid approach for classifying segments of seq...

The field of deep learning has seen significant advancement in recent years. However, much of the existing work has been focused on real-valued numbers. Recent work has shown that a deep learning system using the complex numbers can be deeper for a fixed parameter budget compared to its real-valued counterpart. In this work, we explore the benefits...

Spiking neural networks (SNNs) enable power-efficient implementations due to their sparse, spike-based coding scheme. This paper develops a bio-inspired SNN that uses unsupervised learning to extract discriminative features from speech signals, which can subsequently be used in a classifier. The architecture consists of a spiking convolutional/pool...

While cancer is a heterogeneous complex of distinct diseases, the common underlying mechanism for uncontrolled tumor growth is due to mutations in proto-oncogenes and the loss of the regulatory function of tumor suppression genes. In this paper we propose a novel deep learning model for predicting tumor suppression genes (TSGs) and proto-oncogenes...

*** Cite this paper as: Tavanaei A., Maida A. (2017) Bio-inspired Multi-layer Spiking Neural Network Extracts Discriminative Features from Speech Signals. In: Liu D., Xie S., Li Y., Zhao D., El-Alfy ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science, vol 10639. Springer.*** Spiking neural networks (SNNs) enable...

While cancer is a heterogeneous complex of distinct diseases, the common underlying mechanism for uncontrolled tumor growth is due to mutations in proto-oncogenes and the loss of the regulatory function of tumor suppression genes. In this paper we propose a novel deep learning model for predicting tumor suppression genes (TSGs) and proto-oncogenes...

Spiking neural networks (SNNs) have advantages over traditional, non-spiking networks with respect to bio-realism, potential for low-power hardware implementations, and theoretical computing power. However, in practice, spiking networks with multi-layer learning have proven difficult to train. This paper explores a novel, bio-inspired spiking convo...

Hierarchical feature discovery using non-spiking convolutional neural networks (CNNs) has attracted much recent interest in machine learning and computer vision. However, it is still not well understood how to create a biologically plausible network of brain-like, spiking neurons with multi-layer, unsupervised learning. This paper explores a novel...

Spiking neural networks (SNNs) with adaptive synapses reflect core properties of biological neural networks. Speech recognition, as an application involving audio coding and dynamic learning, provides a good test problem to study SNN functionality. We present a novel and efficient method that learns to convert a speech signal into a spike train sig...

Cognitive computing seeks to build applications which model and mimic human thinking. One approach toward achieving this goal is to develop brain-inspired computational models. A prime example of such a model is the class of deep convolutional networks which is currently used in pattern recognition, machine vision, and machine learning. We offer a...

This paper proposes a novel method for protein function recognition using deep learning. Recently, deep convolutional neural networks (DCNNs) demonstrated high performances in many areas of pattern recognition. Protein function is often associated with its tertiary structure denoting the active domain of a protein. This investigation develops a nov...

The final version of this paper has been published in IEEE-IJCNN 2016 accessible by "http://ieeexplore.ieee.org/document/7727213/". This paper explores modifications to a feedforward five-layer spiking convolutional network (SCN) of the ventral visual stream [Masquelier, T., Thorpe, S., Unsupervised learning of visual features through spike timing...

This paper explores a novel hybrid approach for classifying sequential data such as isolated spoken words. The approach combines a hidden Markov model (HMM) with a spiking neural network (SNN). The HMM, consisting of states and transitions, forms a fixed backbone with nonadaptive transition probabilities. The SNN, however, implements a Bayesian com...

This paper reports the results of experiments to develop a minimal neural network for pattern classification. The network uses biologically plausible neural and learning mechanisms and is applied to a subset of the MNIST dataset of handwritten digits. The research goal is to assess the classification power of a very simple biologically motivated me...

Unsupervised of different types of activity in video data has many applications such as anomaly detection, automated tagging of video for search, and cognitive modeling. Topic models originally used in corpus analysis have recently been used to identify different types of activities in videos. Among topic models, probabilistic latent semantic analy...

This paper demonstrates that feature acquisition systems composed of spiking neurons trained by spike-timing-dependent plasticity (STDP) can effectively be scaled using General-Purpose computing on Graphics Processing Units (GPGPU). Previous studies have demonstrated the efficacy of such systems for classes with low intra-class variability. Paralle...

Visual inspection of neuroimagery is suscepti-ble to human eye limitations. Computerized methods have been shown to be equally or more effective than human clinicians in di-agnosing dementia from neuroimages. Nev-ertheless, much of the work involves the use of domain expertise to extract hand–crafted features. The key technique in this paper is the...

Handwritten character recognition has been an active area of research. However, because of the recent advancements in mobile devices with limited amount of memory and computational power, efficient and simple algorithms for both online and offline character recognition have become more appealing. In this work, an efficient character recognition sys...

Proceedings of the Sixteenth Annual Meeting of the Berkeley Linguistics Society (1990), pp. 530-540

This research models human performance in Dalla Bella, Peretz, and Aronoff (2003) melody recognition study. They compared performance between musicians and nonmusicians in the perception and recognition of isolated melodies. Inspired by cohort theory, they used a gating task to identify three cognitive events in the melody perception/recognition pr...

This research models human performance in the Dalla Bella, Peretz, and Aronoff melody recognition study. They compared performance between musicians and nonmusicians in the recognition (and perception) of melodies. They used a gating task to identify three events in the melody perception/recognition process. These were the familiarity emergence poi...

Understanding how sequences are learned and encoded is a key component to understanding cognition. We present a recruitment model in which sequences are learned via the hierarchical binding of features across time. Learning in the model is unsupervised and occurs within a single presentation of the input. The topology and learning mechanisms allow...

The generalized multilayer perceptron (gMLP) augments the connections in the multilayered perceptron (MLP) architecture to include all possible non-recurrent connections. The layered arbitrarily connected network (lACN) has connections from input nodes to output nodes in addition to the connections included in a MLP. In this paper the performance o...

Our work describes the simulation of a planar network of spiking IfF neurons on graphics processing hardware. The described approach adds to the fast-growing field of general-purpose computation on GPUs (GPGPU). We provide an in-depth explanation of the steps involved in implementing the network using programmable shading hardware. We replicated si...

The generalized multilayer perceptron (gMLP) generalizes the multilayered perceptron (MLP) architecture to a fully connected feedforward architecture where connections are not restricted to adjacent layers. In this paper the performance of MLP and gMLP networks trained using the Levenberg-Marquardt method are compared. A number of different functio...

CajunBot, an autonomous ground vehicle and a finalist in the 2005 DARPA Grand Challenge, is built on the chassis of MAX IV, a six-wheeled ATV. Transformation of the ATV to an AGV (Autonomous Ground Vehicle) re-quired adding drive-by-wire control, LIDAR sensors, an INS, and a computing system. Significant innovations in the core computational algori...

Weight-perturbation (WP) algorithms for supervised and/or reinforcement learning offer improved biological plausibility over backpropagation because of their reduced circuitry requirements for realization in neural hardware. This paper explores the hypothesis that biological synaptic noise might serve as the substrate by which weight perturbation i...

Synchrony-driven recruitment learning addresses the question of how arbitrary concepts, represented by synchronously active ensembles, may be acquired within a randomly connected static graph of neuron-like elements. Recruitment learning in hierarchies is an inherently unstable process. This paper presents conditions on parameters for a feedforward...

The temporal correlation hypothesisproposes using distributed synchrony for the binding of different stimulus features. However, synchronized spikes must travel over cortical cir- cuits that have varying-length pathways, leading to mismatched arrival times. This raises the question of how initial stimulus-dependent synchrony might be preserved at a...

Delayed-response tasks (DRTs) have been used to assess working memory (WM) processes in human and nonhuman animals. Experiments have shown that the basal ganglia (BG) and dorsolateral prefrontal cortex (DLPFC) subserve DRT performance. Here, we report the results of simulation studies of a systems-level model of DRT performance. The model was train...

The local path-planning and obstacle-avoidance module used in the CajunBot, six-wheeled, all-terrain, autonomous land rover is described. The module is designed for rapid subgoal extraction in service of a global navigation system that follows GPS-supplied waypoints. The core algorithm is built around a grid-based, linear-activation field (a type o...

Weight-perturbation (WP) algorithms for supervised and/or reinforcement learning offer improved biological plausibility over backpropagation because of their reduced circuitry requirements for realiza-tion in neural hardware. All such algorithms use some form of information source — a means to compare weight changes with changes in output error — t...

Recruitment learning in hierarchies is an inherently unstable process (Valiant, 1994). This paper presents conditions on parameters for a feedforward network to ensure stable recruitment hierarchies. The parameter analysis is conducted by using a stochastic population approach to model a spiking neural network. The resulting network converges to ac...

We present a single-layer recurrent neural network that im- plements novelty detection for spatiotemporal patterns. The architecture is based on the structure of region CA3 in the hippocampus, which is believed to implement this function. Through analysis and numerical simulation we generate the- orems that constrain the operation of this network....

rdinate mapping for reuse. Motion control is based on an optimization procedure that combines ideas from Fox, Burgard, and Thrun #1997# and Hong et al #1996#, and takes into account the kinematic and dynamic constraints of the robot. The complete architecture of the resulting local #sensor-based# navigation system is shown below. Partially supporte...