Introduction to multi-layer feed-forward neural networks

By Daniel Svozil, Vladimir Kvasnicka, Jiri Pospíchal. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, neutral): “Feed-forward Neural Networks (FNNs) [25] (a.”
LSTM and GRU Neural Network Performance Comparison Study: Taking Yelp Review Dataset as an Example (2020, background): “Then there is a layer of neural network, which can be configured as LSTM or GRU, because more neural network layers can improve the abstract processing ability[10].”
Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach (2020, background): “nonlinear features and has better performance than support vector machines (SVMs) [18] and feedforward neural network (FFNN) [19].”
Learning semantic program embeddings with graph interval neural network (2020, methodology): “Aer GINN computes the state vector for each node, and in turn the entire graph (by aggregating the states of all nodes), we train a feed-forward neural network (Svozil et al. 1997) to predict (using the representation of the entire graph) whether or not a method is buggy.”
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing (2019, methodology): “Among the existing ML methods, deep learning, by leveraging artificial neural networks (ANNs) [16] to learn the deep representation of the data, has resulted in an amazing performance in multiple tasks, including image classification, face recognition, and so on.”
On the Impact of Data Set Size in Transfer Learning Using Deep Neural Networks (2016, methodology): “Concretely, the FNN computes a weighted sum of the inputs, zl i, as follows [65]: z i = sl ∑”
Edge Computing in Industrial Internet of Things: Architecture, Advances and Challenges (2020, unknown): “As a new branch of machine learning method, deep learning uses artiﬁcial neural networks [128] to ﬁt and learn features of historical data, which has achieved remarkable results in target detection, image recognition, and other ﬁelds.”
Deep learning in bioinformatics (2016, methodology): “As in Table 2, we categorized deep learning architectures into four groups: deep neural network (DNN) [104-108], convolutional neural network (CNN) [109111], recurrent neural network (RNN) [112-116], and modified neural network (MNN) [24, 117-119].”
A Classification-Based Surrogate-Assisted Evolutionary Algorithm for Expensive Many-Objective Optimization (2019, background): “Feedforward neural networks (FNNs) are one type of artificial neural networks in which connections between the neurons do not form a cycle [55], and they have been widely applied in SAEAs [56].”
Comprehensive Review of Artificial Neural Network Applications to Pattern Recognition (2019, background): “Importantly, more research focuses on the current hotspots ANN models like SAE, GAN, CNN, DBN, RNN, RBM, TDNN, Reservoir computing, SLP, MLP, Transformer model, etc.”