… In this section, we explore how the topology of the activation space changes across layers …
experiments will largely be evaluated by exploring and comparing the qualitative properties of …

… to fully explore and investigate the effects of depth, width, shapes, activation functions, and
various combinations of these factors on the topologychanging power of neural networks. …

… learning limitations from small and noisy training sets, we propose a multi-task multichannel
topological convolutional neural network (MM-TCNN). We demonstrate that TopologyNet …

… method based on Topological Data Analysis (TDA) and CNN, named TDA-CNN. This
method … Furthermore, we explore ways to reduce the additional computational burden of TDA …

… physics-based topology optimization, we explore a data-driven approach that can quickly …
a deep learning approach based on a 3D encoder-decoder Convolutional Neural Network …

… approach, designed to explore the dynamic topological evolution of convolutional kernels in
neural networks… Our methodology involves training two distinct neural network architectures …

… We evaluate the proposed persistent convolutional neural network (PCNN) model on the
task of music auto-tagging, a multi-label classification task that aims at assigning tags such as …

… In their work, the topology optimization … deep learning with topology optimization, paving
the way for subsequent researchers. We call the methods based on deep neural networks as …

… Given a convolutional neural network with parameters \(\theta \) and a random Gaussian
direction v with dimensions compatible with \(\theta \), \(\overline{v}\) is computed as \(\overline{v…

… Convolutional neural networks (CNNs) and related variants are widely used for image
processing problems such as object segmentation and classification [27]. While most of this large …