In this paper we examine the possibility of using artificial intelligence (AI) to improve academic advisement of students within the School of computing and information technology (SCIT) at the University of Technolog...
In this paper we examine the possibility of using artificial intelligence (AI) to improve academic advisement of students within the School of computing and information technology (SCIT) at the University of technology, Jamaica (Utech). Described as one of the important challenges facing academics [1], academic advisement plays a vital role in student completion. All students at Utech are assigned academic advisors and encouraged to access advisors for advisement. Each faculty manages the process internally. Students are not mandated to seek advisement but are strongly encouraged to do so to allow them to make informed choices related to module selection, academic probation, grade forgiveness, etc. Within SCIT the rate of take up is less than desired resulting in some students going on academic probation, having to switch programs in some cases or failing out of their program. We will explore the automation of the academic advisement process by using AI to push relevant information to students related to their performance. The system will be coded to recognize common situations and contact the students providing information relevant to the situation and schedule an advisement session with the academic advisor (AA).
The attention mechanism has become a pivotal component in artificial intelligence, significantly enhancing the performance of deep learning applications. However, its quadratic computational complexity and intricate c...
详细信息
The attention mechanism has become a pivotal component in artificial intelligence, significantly enhancing the performance of deep learning applications. However, its quadratic computational complexity and intricate computations lead to substantial inefficiencies when processing long sequences. To address these challenges, we introduce Attar, a resistive random access memory(RRAM)-based in-memory accelerator designed to optimize attention mechanisms through software-hardware co-optimization. Attar leverages efficient Top-k pruning and quantization strategies to exploit the sparsity and redundancy of attention matrices, and incorporates an RRAM-based in-memory softmax engine by harnessing the versatility of the RRAM crossbar. Comprehensive evaluations demonstrate that Attar achieves a performance improvement of up to 4.88× and energy saving of 55.38% over previous computing-in-memory(CIM)-based accelerators across various models and datasets while maintaining comparable accuracy. This work underscores the potential of in-memory computing to enhance the efficiency of attention-based models without compromising their effectiveness.
Timely and precise identification of potato leaf diseases plays a critical role in improving crop productivity and reducing the impact of plant pathogens. Conventional detection techniques are often labor-intensive, d...
详细信息
Instance segmentation is a critical component of medical image analysis, enabling tasks such as tissue and organ delineation, and disease detection. This paper provides a detailed comparative analysis of two fine-tune...
详细信息
People are increasingly concerned about their mental health wellness. Scientific studies suggest that online counselling for anxiety and depression is just as effective as in-person treatment. Additionally, journaling...
详细信息
Fog computing extends the cloud paradigm to the edge of the network, thus covering deficiencies that are in cloud computing infrastructure. Security concerns are reduced, but this does not provide a secured platform, ...
详细信息
In Mobile Ad-Hoc Network (MANET), enhancing network lifetime is a challenging issue. Clustering is proved to be a suitable solution to increase scalability and lifetime of MANET. However, it still requires efficient t...
详细信息
Sparse Knowledge Graph(KG)scenarios pose a challenge for previous Knowledge Graph Completion(KGC)methods,that is,the completion performance decreases rapidly with the increase of graph *** problem is also exacerbated ...
详细信息
Sparse Knowledge Graph(KG)scenarios pose a challenge for previous Knowledge Graph Completion(KGC)methods,that is,the completion performance decreases rapidly with the increase of graph *** problem is also exacerbated because of the widespread existence of sparse KGs in practical *** alleviate this challenge,we present a novel framework,LR-GCN,that is able to automatically capture valuable long-range dependency among entities to supplement insufficient structure features and distill logical reasoning knowledge for sparse *** proposed approach comprises two main components:a GNN-based predictor and a reasoning path *** reasoning path distiller explores high-order graph structures such as reasoning paths and encodes them as rich-semantic edges,explicitly compositing long-range dependencies into the *** step also plays an essential role in densifying KGs,effectively alleviating the sparse ***,the path distiller further distills logical reasoning knowledge from these mined reasoning paths into the *** two components are jointly optimized using a well-designed variational EM *** experiments and analyses on four sparse benchmarks demonstrate the effectiveness of our proposed method.
Deep learning algorithms have been rapidly incorporated into many different applications due to the increase in computational power and the availability of massive amounts of ***,both deep learning and ensemble learni...
详细信息
Deep learning algorithms have been rapidly incorporated into many different applications due to the increase in computational power and the availability of massive amounts of ***,both deep learning and ensemble learning have been used to recognize underlying structures and patterns from high-level features to make predictions/*** the growth in popularity of deep learning and ensemble learning algorithms,they have received significant attention from both scientists and the industrial community due to their superior ability to learn features from big *** deep learning has exhibited significant performance in enhancing learning generalization through the use of multiple deep learning *** ensemble deep learning has large quantities of training parameters,which results in time and space overheads,it performs much better than traditional ensemble *** deep learning has been successfully used in several areas,such as bioinformatics,finance,and health *** this paper,we review and investigate recent ensemble deep learning algorithms and techniques in health care domains,medical imaging,health care data analytics,genomics,diagnosis,disease prevention,and drug *** cover several widely used deep learning algorithms along with their architectures,including deep neural networks(DNNs),convolutional neural networks(CNNs),recurrent neural networks(RNNs),and generative adversarial networks(GANs).Common healthcare tasks,such as medical imaging,electronic health records,and genomics,are also ***,in this review,the challenges inherent in reducing the burden on the healthcare system are discussed and ***,future directions and opportunities for enhancing healthcare model performance are discussed.
Machine learning has evolved from a lab curiosity to a widely used technology that is fundamentally reliant on ground truth data for model training and evaluation. This research addresses the challenges in obtaining a...
详细信息
暂无评论