Neural Networks - A Systematic Introduction

By R. Rojas. 1996

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

Classification-based financial markets prediction using deep neural networks (2016, positive): “Stochastic Gradient Descent Following Rojas (1996), we now revisit the backpropagation learning algorithm based on the method of stochastic gradient descent (SGD) algorithm.”
A comparative study of machine learning classifiers for modeling travel mode choice (2017, background): “The cost of constraint156 violation is set to 1.25 and the kernel bandwidth is set to 0.4.157 Inspired by the biological brain, ANNs consist of a set of artificial neurons and directed connections158 between them (e.g. Rojas, 2013).”
Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods (2017, background): “The findings are mostly negative (Rojas, 1996; Š́ıma, 2002; Blum and Rivest, 1993; Bartlett and Ben-David, 1999; Kuhlmann, 2000).”
Sequence classification of the limit order book using recurrent neural networks (2017, background): “See Rojas (1996); Graves (2013) for a further description of stochastic gradient descent as it pertains to recurrent neural networks.”
Visualizing Big Data with augmented and virtual reality: challenges and research agenda (2015, methodology): “Those are the basis for data analysis techniques such as Data Mining [39, 46–49], Neural Networks [41, 50–52], Machine Learning [53–55], Signal Processing [56–58] and Visualization Methods [59–61].”
Quantum simulations with cold trapped ions (2009, methodology): “14N [Rojas 1996].”
An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring (2009, methodology): “The details of the LM algorithm for training feedforward neural networks can be found in Rojas (1996).”
Understanding adversarial training: Increasing local stability of supervised models through robust optimization (2015, unknown): “we have that the choice that maximizes the right-hand side is exactly the quantity in equation 2. Since the 2 gradient r xJ(;x;y) can be computed efﬁciently using backpropagation (see, for example, [19]), this approach for generating adversarial examples is rather fast. In the sequel we will show ho”
Experimental demonstration of associative memory with memristive neural networks (2009, background): “In such configuration, our network behaves essential ly as a linear perceptron [ 32 ], [33], [34], although different connection schemes are possible.”
The CART decision tree for mining data streams (2014, background): “The most popular are neural networks [29] [30], k-nearest neighbors [4] or decision trees [3] [26] [27], which are within the scope of this paper.”
On the Complexity of Neural Network Classifiers: A Comparison Between Shallow and Deep Architectures (2014, unknown): “IS A WELL-KNOWN RESULT AVAILABLE IN [26]”
Feature selection for support vector machines by means of genetic algorithm (2003, background): “ing and reinforcement learning (e.g. [RusNor95, Rojas96 ]). In corrective”
A new methodology to interpret high resolution measurements of net carbon fluxes between terrestrial ecosystems and the atmosphere (2012, methodology): “2 Backpropagation algorithm The backpropagation algorithm is a widely employed method for supervised learning of feedforward ANNs (Rojas, 1996; Rumelhart et al., 1986).”
STDP and STDP variations with memristors for spiking neuromorphic learning systems (2013, methodology): “This contrasts to more traditional learning rules, like backpropagation (Rojas, 1996), where ﬁrst neurons and synapses perform signal aggregation and neural state update (we call this here “performing phase”) and then synaptic updates are computed and applied (we call this here “weight update…”
Deep Learning for Time-Series Analysis (2017, methodology): “The reader is referred to [49] for a thorough description of architectural alternatives such as Restricted Boltzmann Machines (RBM), Hopﬁeld Networks and Auto-Encoders, as well as for a detailed explanation of the Backpropagation algorithm.”