A fast FPGA-based deep convolutional neural network using pseudo parallel memories

The application of deep learning technology has increased rapidly in recent years. Technologies in deep learning increasingly emulate natural human abilities, such as knowledge learning, problem-solving, and decision-making. In general, deep learning can carry out self-training without repetitive programming by humans. Convolutional neural networks (CNNs) are deep learning algorithms commonly used in wide applications. CNN is often used for image classification, segmentation, object detection, video processing, natural language processing, and speech recognition. CNN has four layers: convolution layer, pooling layer, fully connected layer, and non-linear layer. The convolutional layer uses kernel filters to calculate the convolution of the input image by extracting the fundamental features. The pooling layer combines two successive convolutional layers. The third layer is the fully connected layer, commonly called the convolutional output layer. The activation function defines the output of a neural network, such as 'yes' or 'no'. The most common and popular CNN activation functions are Sigmoid, Tanh, ReLU, Leaky ReLU, Noisy ReLU, and Parametric Linear Units. The organization and function of the visual cortex greatly influence CNN architecture because it is designed to resemble the neuronal connections in the human brain. Some of the popular CNN architectures are LeNet, AlexNet and VGGNet.

Convolutional neural networks (CNN) is a widely known deep learning architecture and achieves higher accuracies in speech processing and computer vision applications. CNN has arisen as best option in the fields such as video surveillance, mobile robot vision, smart factories, and medical diagnostics. CNN has shown its tremendous potential for image understanding in Cardio-Vascular (CV) systems. But, the tremendous potential of CNNs came up with additional computational burden. To get an outstanding performance of CNN-based algorithms, it requires large amount of enormous applications and memory resources. Matrix multiplication (MM) is the most fundamental computational operation taking place in CNN. Researchers in this field found that multiplication operation is the most resource-intensive and power-hungry operation in CNN. This work aims to design an FPGA-based CNN using systolic array which can improve both the accuracy and hardware efficiency of convolutional neural network. Here, we made design optimisation in multiplier unit which brings a significant impact on overall performance of convolutional neural networks.

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

Algorithms based on deep learning are taking off as solutions to several problems in numerous fields. Numerous deep learning architectures like convolutional neural networks, recurrent neural networks, deep belief networks, artificial neural networks and deep neural networks have been used in fields such as audio recognition, machine vision, processing of natural language, recognition of speech, social network filtering, computer vision, translating languages and bioinformatics. One such application of deep learning architectures is object detection. Object detection in satellite and aerial imagery undertakes an important role in a long list of applications and has allured a lot of attention which resulted in exceptional progress in recent years. It has abundant uses in various fields such as surveillance, military, national security, urban planning, environmental applications, traffic control and forestry. Several issues like varying size, background and orientation of the target object make the automatic detection of target in satellite imagery a challenging issue. Recent research in this field has given better speed and accuracy to the detection of the target object. With the rise in the data being generated by the Earth Observation programs, it is becoming much more imperative to find better and efficient ways to exploit this data by improving upon the existing Deep Learning research. In this paper, we bring forth a wide-ranging analysis of the recent advancements in methods of object detection based on deep learning to recognize the objects in satellite imagery.KeywordsDeep learningObject detectionSatellite imageryRemote sensingYou Only Look Once (YOLO)You Only Look Twice (YOLT)Single Shot Detector (SSD)Convolutional Neural Networks (CNN)Faster Region-based Convolutional Neural Networks (Faster RCNN)Hybrid Deep Convolutional Neural Network (HDNN)Satellite Imagery Multiscale Rapid Detection with Windowed Networks (SIMRDWN)

Deep learning methodologies have had a major impact on performance across a wide variety of machine learning tasks, and speech recognition is no exception. We describe a set of deep learning techniques that proved to be particularly successful in achieving performance gains in word error rate on a popular large vocabulary conversational speech recognition benchmark task (“Switchboard”). We found that the best performance is achieved by combining features from both recurrent and convolutional neural networks. We compare two recurrent architectures: partially unfolded nets with max-out activations and bidirectional long short-term memory nets. In addition, inspired by the success of convolutional networks for image classification, we designed a convolutional net with many convolutional layers and small kernels that create a receptive field with more nonlinearity and fewer parameters than standard configurations. When combined, these neural networks achieve a word error rate of 6.2% on this difficult task; this was the best reported rate at the time of this writing and is even more remarkable given that human performance itself is estimated to be 4% on this data.

Sound-event recognition often utilizes time-frequency analysis to produce an image-like spectrogram that provides a rich visual representation of original signal in time and frequency. Convolutional Neural Networks (CNN) with the ability of learning discriminative spectrogram patterns are suitable for sound-event recognition. However, there is relatively little effort that CNN makes full use of the important temporal information. In this paper, we propose MCRNN, a Convolutional Recurrent Neural Networks (CRNN) architecture for sound-event recognition, the letter “M” in the name “MCRNN” of our model denotes the multi-sized convolution filters. Richer features are extracted by using several different convolution filter sizes at the last convolution layer. In addition, cochleagram images are used as the input layer of the network, instead of the traditional spectrogram image of a sound signal. Experiments on the RWCP dataset shows that the recognition rate of the proposed method achieved 98.4% in clean conditions, and it robustly outperforms the existing methods, the recognition rate increased by 0.9%, 1.9% and 10.3% in 20 dB, 10 dB and 0 dB signal-to-noise ratios (SNR), respectively.

This article concerns comparative studies on the Automatic Speech Recognition (ASR) model incorporated with the Large Language Model (LLM) used for medical interviews. The proposed solution is tested on polish language benchmarks and dataset with medical interviews. The latest ASR technologies are based on convolutional neural networks (CNNs), recurrent neural networks (RNNs) and Transformers. Most of them work as end-to-end solutions. The presented approach in the case of the Whisper model shows a two-stage solution with End-To-End ASR and LLM working together in a pipeline. The ASR output is an input for LLM. The LLM is a component by which the output from ASR is corrected and improved. Comparative studies for automatic recognition of the Polish language between modern End-To-End deep learning architectures and the ASR hybrid model were performed. The medical interview tests were performed with two state-of-the-art ASR models: OpenAI Whisper incorporated with LLM and Scribe ElevenLabs. Additionally, the results were compared with five more end-to-end models (QuartzNet, FastConformer, Wav2Vec 2.0 XLSR and ESPnet Model Zoo) on Mozilla Common Voice and VoxPopuli databases. Tests were conducted for clean audio signal, signal with bandwidth limitation, and degraded. The tested models were evaluated on the basis of Word Error Rate (WER) and Character Error Rate (CER). The results show that the Whisper model performs by far the best among the open-source models. ElevenLabs Scribe model, on the other hand, performs best for Polish on both general benchmark and medical data.

Convolutional neural networks (CNNs) have demonstrated the state-of-the-art performances on automatic speech recognition. Softmax activation function for prediction and minimizing the cross-entropy loss is employed by most of the CNNs. This paper proposes a new deep architecture in which two heterogeneous classification techniques named as CNN and support vector machines (SVMs) are combined together. In this proposed model, features are learned using convolution layer and classified by SVMs. The last layer of CNN i.e. softmax layer is replaced by SVMs to efficiently deal with high dimensional features. This model should be interpreted as a special form of structured SVM and named as convolutional support vector machine (CSVM). Instead of training each component separately, the parameters of CNN and SVMs are jointly trained using frame level max-margin, sequence level max-margin, and state-level minimum Bayes risk criterion. The performance of CSVM is checked on TIMIT and Wall Street Journal datasets for phone recognition. By incorporating the features of both CNN and SVMs, CSVM improves the result by 13.33% and 2.31% over baseline CNN and segmental recurrent neural networks respectively.

Convolutional neural network (CNN) is the primary technique that has greatly promoted the development of computer vision technologies. However, there is little research on how to allocate parameters in different convolution layers when designing CNNs. We research mainly on revealing the relationship between CNN parameter distribution, i.e., the allocation of parameters in convolution layers, and the discriminative performance of CNN. Unlike previous works, we do not append more elements into the network, such as more convolution layers or denser short connections. We focus on enhancing the discriminative performance of CNN through varying its parameter distribution under strict size constraint. We propose an energy function to represent the CNN parameter distribution, which establishes the connection between the allocation of parameters and the discriminative performance of CNN. Extensive experiments with shallow CNNs on three public image classification data sets demonstrate that the CNN parameter distribution with a higher energy value will promote the model to obtain better performance. According to the motivated observation, the problem of finding the optimal parameter distribution can be transformed into an optimization problem of finding the biggest energy value. We present a simple yet effective guideline that uses balanced parameter distribution to design CNNs. Extensive experiments on ImageNet with three popular backbones, i.e., AlexNet, ResNet34, and ResNet101, demonstrate that the proposed guideline can make consistent improvements upon different baselines under strict size constraint.

As robots and machines become more reliable, developing tools that utilize their potential in manufacturing and beyond is an important step being addressed by many, including the LIMDA team at the University of Alberta. A common and effective means to improve artificial performance is through optical character recognition methods. Within the category of artificial intelligence under classification machine learning, research has focussed on the benefits of convolutional neural networks (CNN) and the improvement provided compared to its parent method, neural networks. Neural networks serious flaw comes from memorization and the lack of learning about what the images contain, while CNN's combat those issues. CNN’s are designed to connect information received by the network and begins to closely mimic how humans experience learns. Using the programming language Python and machine learning libraries such as Tensorflow and Keras, different versions of CNN’s were tested against datasets containing low-resolution images with handwritten characters. The first two CNN’s were trained against the MNIST database against digits 0 through 9. The results from these tests illustrated the benefits of elements like max-pooling and the addition of convolutional layers. Taking that knowledge a final CNN was written to prove the accuracy of the algorithm against alphabet characters. After training and testings were complete the network showed an average 99.34% accuracy and 2.23% to the loss function. Time-consuming training epochs that don’t wield higher or more impressive results could also be eliminated. These and similar CNN’s have proven to yield positive results and in future research could be implemented into the laboratory to improve safety. Continuing to develop this work will lead to better translators for language, solid text to digital text transformation, and aides for the visual and speech impaired.

This study compared popular Deep Learning (DL) architectures to classify machining surface roughness using sound and force data. The DL architectures considered in this study include Multi-Layer Perceptron (MLP), Convolution Neural Network (CNN), Long Short-Term Memory (LSTM), and transformer. The classification was performed on the sound and force data generated during machining aluminum sheets for different levels of spindle speed, feed rate, depth of cut, and end-mill diameter, and it was trained on 30 s machining data (10–40 s) of the machining experiments. Since a raw audio waveform is seldom used in DL models, Mel-Spectrogram and Mel Frequency Cepstral Coefficients (MFCCs) audio feature extraction techniques were used in the DL models. The results of DL models were compared for the training–validation accuracy, training epochs, and training parameters of each model. Although the roughness classification by all the DL models was satisfactory (except for CNN with Mel-Spectrogram), the transformer-based modes had the highest training (>96%) and validation accuracies (≈90%). The CNN model with Mel-Spectrogram exhibited the worst training and inference accuracy, which is influenced by limited training data. Confusion matrices were plotted to observe the classification accuracy visually. The confusion matrices showed that the transformer model trained on Mel-Spectrogram and the transformer model trained on MFCCs correctly predicted 366 (or 91.5%) and 371 (or 92.7%) out of 400 test samples. This study also highlights the suitability and superiority of the transformer model for time series sound and force data and over other DL models.

Convolutional neural network (CNN) consists of a few pairs of both convolution layer and subsampling layer. Thus it has more hidden layers than multi-layer perceptron. With the increased layers, the size of convolution mask ultimately determines the total number of weights in CNN because the mask is shared among input images. It also is an important learning factor which makes or breaks CNNs learning. Therefore, this paper proposes the best method to choose the convolution size and the number of layers for learning CNN successfully. Through our face recognition with vast learning examples, we found that the best size of convolution mask is 5 by 5 and 7 by 7, regardless of the number of layers. In addition, the CNN with two pairs of both convolution and subsampling layer is found to make the best performance as if the multi-layer perceptron having two hidden layers does.

Deep Convolutional Neural Networks for Large-scale Speech Tasks

Steering angle prediction plays a crucial role in the control of Autonomous Vehicles (AVs) and has garnered the interest of researchers, manufacturers, and insurance companies within the automotive industry. Various Deep Learning (DL) architectures have been utilized to forecast the steering angle of AVs across different scenarios. An examination focusing on steering angle prediction through deep learning algorithms can assist seasoned researchers in pinpointing areas that necessitate further advancement. Additionally, newcomers in the field can utilize this study as a foundation. This paper offers an extensive analysis of the recent progress achieved in DL architectures concerning the steering angle prediction of AVs. A comprehensive taxonomy outlining the application of DL in steering angle prediction of AVs has been developed. The survey provides a succinct synthesis, summary, and analysis of research findings. It is evident that Convolutional Neural Network (CNN) is the preferred choice among researchers for predicting the steering angle of autonomous vehicles, compared to other DL architectures. Furthermore, existing research challenges have been identified. The primary obstacle encountered in DL-based steering angle prediction of AVs is the scarcity of real-world datasets, leading researchers to heavily rely on data generated from simulated environments. Lastly, potential alternative approaches to address the identified research challenges have been suggested, indicating promising avenues for future research endeavours.

Sentiment Analysis was a process for identifying whether a source of text contains certain opinions, emotions, and polarity. Twitter Sentiment Analysis was a process for identifying sentiment and polarity on tweet. Twitter Sentiment Analysis provided a way for did survey about public sentiment to product, or particular even through collections of tweet. Main problem in sentiment identifying was how to determine classification model that gave high accuracy to classifying sentiment of tweet. One of the method for classifying sentiment of tweet was Deep Learning. Convolutional Neural Network (CNN) was special type of architecture from Deep Learning that its architecture had convolution layer. Convolution layer was important for extract relevant feature from text for classifying sentiment. The objective of this research was for found out the best CNN model for classifying sentiment of tweet. By using a dataset of tweets about public opinion on the Smartfren 4G network service, we searched the best CNN model using 6 combination parameters, that is the computational eficiency method, window size, and dimension of word embedding for parameters in Word2Vec Skip-gram model, then activation function in convolution layer, dropout rate, and pool size in pooling layer for parameters in CNN. The test is done using 10-fold cross validation for each search for the best parameter value and produced the best CNN model with an accuracy value of 88,21%.