Advanced search

Showing result 1 - 5 of 10 essays matching the above criteria.

  1. 1. Building a Deep Neural Network From Scratch

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Fredrik Sundström; Samppa Raittila; [2023]
    Keywords : ;

    Abstract : Machine learning is becoming increasingly common in our society and is predictedto have a major impact in the future. Therefore, it would be both interesting and valuable tohave a deep understanding of one of the most used algorithms in machine learning, deepneural network. READ MORE

  3. 2. Basil-GAN

    University essay from KTH/Matematisk statistik

    Author : Jonatan Risberg; [2022]
    Keywords : GAN; mathematical statistics; deep neural networks; generative models; latent space exploration; sequential data; GAN; matematisk statistik; djupa neurala nätverk; generativa modeller; utforskning av latenta rum; sekventiell data;

    Abstract : Developments in computer vision has sought to design deep neural networks which trained on a large set of images are able to generate high quality artificial images which share semantic qualities with the original image set. A pivotal shift was made with the introduction of the generative adversarial network (GAN) by Goodfellow et al.. READ MORE

  4. 3. Deep Active Learning for Image Classification using Different Sampling Strategies

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Shahin Saleh; [2021]
    Keywords : Convolutional Neural Network; Deep Active Learning; Deep Learning; Image Classification; Sampling Strategies; SemiSupervised Learning.; Bildklassificering; Faltningsnätverk; Deep Active Learning; Djupinlärning; Semiövervakat lärande; Urvalsstrategier.;

    Abstract : Convolutional Neural Networks (CNNs) have been proved to deliver great results in the area of computer vision, however, one fundamental bottleneck with CNNs is the fact that it is heavily dependant on the ground truth, that is, labeled training data. A labeled dataset is a group of samples that have been tagged with one or more labels. READ MORE

  5. 4. Attractors of autoencoders : Memorization in neural networks

    University essay from Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

    Author : Jonas Strandqvist; [2020]
    Keywords : machine learning; overfitting; memorization; neural network; autoencoder; attractor; Jacobian; eigenvalue; CIFAR10; random data; ReLU; bias;

    Abstract : It is an important question in machine learning to understand how neural networks learn. This thesis sheds further light onto this by studying autoencoder neural networks which can memorize data by storing it as attractors. READ MORE

  6. 5. Comparing Catastrophic Interference between Incremental Moment Matching-Mean and Hard Attention to the Task

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Quintus Roos; William Lilliesköld; [2020]
    Keywords : ;

    Abstract : When a neural networks trained on data to solve one problem is trained on new data to solve another problem it tends to forget what it had previously knew that made it able to solve the first problem. This phenomenon is called Catastrophic Interference. READ MORE