Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 67 for “"Convolutional layer"”.
-
Convolutional Layer Implementations in High-Level Synthesis for FPGAs
… (HLS). We propose an alternative approach for convolutional neural networks within the HLS4ML framework. Using the new approach on benchmark convolutional neural network (CNN) models, we show a potential reduction of FPGA critical resource consumption by up to 30% and latency by up to 12%. …
-
Whetstone Trained Spiking Deep Neural Networks to Spiking Neural Networks
… neural network which uses multiple structured layers to extract features from the input. Spiking neural networks are another type of artificial neural network which closely mimic biology with time dependent pulses to transmit information. Whetstone is a training algorithm for spiking deep …
-
Improving Facial Action Unit Recognition Using Convolutional Neural Networks
… limited AU-coded training data. Most recently, convolutional neural networks (CNNs) have shown promise on facial AU recognition. However, CNNs are often overfitted and do not generalize well to unseen subject due to limited AU-coded training images. In order to improve the performance of facial …
-
Low-power, low-complexity image classification with optical sensors
Convolutional Neural Networks (CNNs) have become a very effective tool in image estimation and inference (e.g., noise reduction, segmentation, object recognition). However, CNNs are difficult to deploy in resource-constrained scenarios, such as edge devices, IoT sensors, mobile embedded systems, …
-
Image classification with directional image sensors
Traditional electronic implementations of CNNs (Convolutional Neural Networks) suffer from high power consumption and limited processing speed, hindering deployment in resource-constrained scenarios. Leveraging the power of photonics, an innovative imaging device has been developed in Prof. …
-
Design and implementation of a convolutional neural network using tensor-train decomposition
… thesis, we introduce a new formulation of the convolutional layer and verify a new training algorithm using Bayesian inference. Here we refer to any neural networks with any tensor-train-layers and trained by Bayesian training algorithm as a Bayesian TensorNet (BTN). The BTN provides a …
-
Unique Image Representation as a Tensor
… tasks where data features are used. Popular convolutional layer used in various neural networks reduces information and can not reconstruct original image. In this thesis , we present several examples where these coefficients are used in image classification tasks for a standard data set.
-
Lipreading with convolutional and recurrent neural network models
… and tested on the AVICAR dataset, including one convolutional neural network (CNN) model with fully connected classification layer, and one recurrent neural network (RNN) model with convolutional layer and one long short-term memory (LSTM) layer to perform the classification on a sequence of …
-
Deep learning for fine-grained visual recognition
… an important task in computer vision. The cross-convolutional-layer pooling method is one of the significant milestones in the development of this field in recent years. Based on the method, we conducted a number of experiments on a new fine-grained car dataset - CompCars. The corresponding …
-
Scoring Single-Sample Pathway Expression Level Using Graph Autoencoder
… among the biological pathways with graph convolutional layer while training the model. We evaluate the proposed method with four different single-sample pathway analysis studies: ssGSEA, GSVA, Pathifier, and kPCA. Since pathway analysis has no ground truth, we examine and perform various …
-
Handling Invalid Pixels in Convolutional Neural Networks
Most neural networks use a normal convolutional layer that assumes that all input pixels are valid pixels. However, pixels added to the input through padding result in adding extra information that was not initially present. This extra information can be considered invalid. Invalid pixels can also …
-
On the performance of convolutional neural networks initialized with Gabor filters.
… popularity due to its various possible usages. Convolutional Neural Networks (CNNs) have been the classic approach taken on by many researchers because of their capability to learn through the parameter space given a sufficient amount of representative data. When observing a fully trained CNN, …
-
Kvantinių skaičiavimų ir algoritmų tyrimas naudojant simuliatorių paprastame personaliniame kompiuteryje /
… quantum simulators. During the study, a quantum convolutional layer for preprocessing images of CIFAR10 dataset was constructed. The output of this layer is used as input for a simple neural network. Also, a hybird model using Grover’s algorithm is created and adapted to perform multiclass …
-
A Novel Feature Maps Covariance Minimization Approach for Advancing Convolutional Neural Network Performance
… a method for boosting the performance of the Convolutional Neural Network (CNN) by reducing the covariance between the feature maps of the convolutional layers. In a CNN, the units of a hidden layer are segmented into the feature/activation maps. The units within a feature map share the weight …
-
Residual Capsule Network
The Convolutional Neural Network (CNN) have shown a substantial improvement in the field of Machine Learning. But they do come with their own set of drawbacks. Capsule Networks have addressed the limitations of CNNs and have shown a great improvement by calculating the pose and transformation of …
-
Representation of 3D and 2D stimuli in AlexNet
… We find as representation evolves from the first convolutional layer to deeper layers, stimuli of the same class tend to come closer together, resulting in separation by class identity. Relu3 units in AlexNet were previously found to display similar 3D selectivity to primate V4 neurons, so we try …
-
Reconstructing and Analyzing Effective Hypersurfaces From Convolutional Neural Network Layers Using AdjointBackMap
There are several methods in the exploration of Convolutional Neural Network’s (CNN’s) inner workings. However, in general, finding the inverse of the function performed by CNN as a whole is an ill-posed problem. We propose an Adjoint Operator-based method to reconstruct, given an arbitrary unit in …
-
Convolutional Neural Network for Sentence Classification
… word2vec representation of words, we propose two convolutional neural networks (CNNs) to solve the multi-label classification problem, namely Parallel CNN and Deep CNN. The Parallel CNN contains four parallel convolutional layers while Deep CNN contains two serial convolutional layers. The …
-
Increasing CNN representational power using absolute cosine value regularization
The Convolutional Neural Network (CNN) is a mathematical model designed to distill input information into a more useful representation. This distillation process removes information over time through a series of dimensionality reductions, which ultimately, grant the model the ability to resist …
-
Articulatory-WaveNet: Deep Autoregressive Model for Acoustic-to-Articulatory Inversion
… architecture is based on a dilated causal convolutional layer structure that improves the Acoustic-to-Articulatory Inversion estimated results for both speaker-dependent and speaker-independent scenarios. The system has been evaluated on the ElectroMagnetic Articulography corpus of Mandarin …
Page 1 of 4