Powerful classifiers as neural networks have long been used to recognise images; these images might depict objects like animals, people or plain text. Distorted images affect the neural network's ability to recognise them, they might be distorted or changed due to distortions related to the camera.Camera related distortions, and how they affect the accuracy, have previously been explored. Recently, it has been proven that images can be intentionally made harder to recognise, an effect that last even after they have been photographed.Such images are known as adversarial examples.The purpose of this thesis is to evaluate how well a neural network can recognise adversarial examples which are also distorted. To evaluate the network, the adversarial examples are distorted in different ways and thereafter fed to the neural network.Different kinds of distortions (rotation, blur, contrast and skew) were used to distort the examples. For each type and strength of distortion the network's ability to classify was measured.Here, it is shown that all distortions influenced the neural network's ability to recognise images.It is concluded that the type and strength of a distortion are important factors when classifying distorted adversarial examples, but also that some distortions, rotation and skew, are able to keep their characteristic influence on the accuracy, even if they are influenced by other distortions.

No description available.

This thesis summarizes our project in building and setting up a Beowulf cluster. The idea of the project was brought forward by the company CGI in Karlstad, Sweden. CGI’s wish is that the project will serve as a starting point for future research and development of a larger Beowulf cluster. The future work can be made by both employees at CGI and student exam projects from universities. The projects main purpose was to construct a cluster by using several credit card sized single board computers, in our case the Raspberry Pi 3. The process of installing, compiling and con- figuring software for the cluster is explained. The MPICH and TensorFlow software platforms are reviewed. A performance evaluation of the cluster with TensorFlow is given. A single Raspberry Pi 3 can perform neural network training at a rate of seven times slower than an Intel system (i5-5250U at 2.7 GHz and 8 GB RAM at 1600 MHz). The performance degraded significantly when the entire cluster was training. The precise cause of the performance degradation was not found, but is ruled out to be in software, either a programming error or a bug in TensorFlow.

When asked to implement a neural network application, the decision concerning what hardware platform to use may not always be easily made. This thesis studies various relevant platforms with regards to performance, power efficiency and usability, with the purpose of providing a basis for such decisions. The hardware platforms which are studied were a GPU, an FPGA and a CPU. The project implements Convolutional Neural Networks (CNN) on the different hardware platforms using several tools and frameworks. The final implementation uses BNN-PYNQ for the implementation on the FPGA and CPU, which provided ready-to-run code and overlays for quantized CNNs and fully connected neural networks. Next, these networks are copied using TensorFlow, and optimized to FP32, FP16 and INT8 precision using TensorRT for use on the GPU. The results indicate that the FPGA outperforms the GPU with a factor of 100 for the CNN networks, and a factor of 1000 on the fully connected networks with regards to inference speed. For power efficiency, the FPGA again outperforms the GPU. The thesis concludes that for a neural network application, an FPGA is preferred if performance is a priority. However, the GPU proved to have a greater ease of use due to the many tools and frameworks available. If easy implementation and high design flexibility is a priority, a GPU is instead recommended.

Since mid to late 2010 image synthesizing using neural networks has become a trending research topic. And the framework mostly used for solving these tasks is the Generative adversarial network (GAN). GAN works by using two networks, a generator and a discriminator that trains and competes alongside each other. In today’s research regarding image synthesis, it is mostly about generating or altering images in any way which could be used in many fields, for example creating virtual environments. The topic is however still in quite an early stage of its development and there are fields where image synthesizing using Generative adversarial networks fails. In this work, we will answer one thesis question regarding the limitations and discuss for example the limitation causing GAN networks to get stuck during training. In addition to some limitations with existing GAN models, the research also lacks more experimental GAN variants. It exists today a lot of different variants, where GAN has been further developed and modified. But when it comes to GAN models where the discriminator has been changed to a different network, the number of existing works reduces drastically. In this work, we will experiment and compare an existing deep convolutional generative adversarial network (DCGAN), which is a GAN variant, with one that we have modified using a deep neuro-fuzzy system. We have created the first DCGAN model that uses a deep neuro-fuzzy system as a discriminator. When comparing these models, we concluded that the performance differences are not big. But we strongly believe that with some further improvements our model can outperform the DCGAN model. This work will therefore contribute to the research with the result and knowledge of a possible improvement to DCGAN models which in the future might cause similar research to be conducted on other GANmodels.

Artificial Neural Networks make up the core of mostMachine Learning algorithms. In the past decade Machine learninghave successfully taken on fields such as image recognition,Data analytics and medical technologies. As the area of usebecome less prone to mistakes, it raises the responsibility lookinto the black box of code and understand it to a deeper level. Inthis project, I built a Deep Neural Network from scratch, withouthigh level libraries, and trained it for a supervised classificationtask. The finished algorithm is flexible and can be adapted toany classification problem. The training method is based onBackpropagation and Gradient Descent. At last, the algorithmwas trained on the Modified National Institute of Standardsand Technology (MNIST) database, and performed with a 77%prediction acccuracy. There are a few optimization methods yetto be tested to further increase the performance. / Artificiella neurala nätverk utgör kärnan i de flesta maskininlärningsalgoritmer idag. Under det senaste decenniet har maskininlärning framgångsrikt tagit an områden som bildigenkänning, dataanalys och medicinsk teknik. När användningsområdena blir mindre benägna till misstag, ökar ansvaret av att titta under huven och förstå den djupare nivåkoden. I denna studie var syftet att bygga ett djupt neuralt nätverk från grunden, utan högnivåbibliotek, och träna det för en övervakad klassificeringsuppgift. Den färdiga algoritmen är flexibel och kan designas för flera klassificeringsproblem. Nätverkets träningsmetod är baserad på Backpropagation och Gradient Descent. Valideringsdatan kunde till slut köras med 77% korrekt noggrannhet, och det finns finns ytterligare optimeringsmetoder att testa för att höja prestationen. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

No description available.

Machine learning has achieved great success in recent years, especially the deep learning algorithms based on Artificial Neural Network. However, high performance and large memories are needed for these models , which makes them not suitable for IoT device, as IoT devices have limited performance and should be low cost and less energy-consuming. Therefore, it is necessary to optimize the deep learning models to accommodate the resource-constrained IoT devices. This thesis is to seek for a possible solution of optimizing the ANN models to fit into the IoT devices and provide a hardware implementation of the ANN accelerator on FPGA. The contribution of this thesis mainly lies in two aspects: 1). analyze the sparsity in the two mainstream deep learning models – DBN and CNN. The DBN model consists of two hidden layers with Restricted Boltzmann Machines while the CNN model consists of 2 convolutional layers and 2 sub-sampling layer. Experiments have been done on the MNIST data set with the sparsity of 75%. The ratio of the multiplications resulting in near-zero values has been tested. 2). FPGA implementation of an ANN accelerator. This thesis designed a hardware accelerator for the inference process in ANN models on FPGA (Stratix IV: EP4SGX530KH40C2). The main part of hardware design is the processing array consists of 256 Multiply-Accumulators array, which can conduct multiply-accumulate operations of 256 synaptic connections simultaneously. 16-bit fixed point computation is used to reduce the hardware complexity, thus saving power and area. Based on the evaluation results, it is found that the ratio of the multiplications under the threshold of 2-5 is 75% for CNN with ReLU activation function, and is 83% for DBN with sigmoid activation function, respectively. Therefore, there still exists large space for complex ANN models to be optimized if the sparsity of data is fully utilized. Meanwhile, the implemented hardware accelerator is verified to provide correct results through 16-bit fixed point computation, which can be used as a hardware testing platform for evaluating the ANN models.

No description available.

This study aims to modify Vision Transformer (ViT) to achieve higher accuracy. ViT is a model used in computer vision to, among other things, classify images. By applying ViT to the MNIST data set, an accuracy of approximately 98% is achieved. ViT is modified by implementing a method called Histogram of Oriented Gradients (HOG) in two different ways. The results show that the first approach with HOG gives an accuracy of 98,74% (setup 1) and the second approach gives an accuracy of 96,87% (patch size 4x4 pixels). The study shows that when HOG is applied on the entire image, a better accuracy is obtained. However, no systematic optimization has taken place, which makes it difficult to draw conclusions with certainty.