Algorithm and implementation of an associative memory for oriented edge detection using improved clustered neural networks

Danilo, Robin; Jarollahi, Hooman; Gripon, Vincent; Coussy, Philippe; Conde-Canencia, Laura; Gross, Warren J.

doi:10.1109/iscas.2015.7169193

Cited by 7 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the CNN implementation, the major part of the area (46%) is used for registers, then the storing module (33%) and finally the retrieving module (21%). The high register cost is due to the fact that the implementation [3] uses two times more memory elements for the memory array than needed (from Eq. 3).…”

Section: Complexity Analysismentioning

confidence: 99%

“…With the CNN configuration studied here, only 25 instances of the "Yeast data set" can be stored with an error rate under 0.01, whereas the number of instances which can be stored in CNN [3] R-CNN Registers 1.36 × 10 6 1.63 × 10 6 (+20%) Storing 0.97 × 10 6 1.17 × 10 6 (+20%)…”

Section: Complexity Analysismentioning

confidence: 99%

“…with a good message retrieval ability (probability to retrieve a message). Based on binary units, binary connections and a simple decoding algorithm, this associative network model allows efficient fully-parallel hardware implementations [7,8,3]. However, like other models of associative networks [9], diversity strongly depends on the distribution of stored messages.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Restricted Clustered Neural Network for Storing Real Data

Danilo

Coussy

Conde-Canencia

et al. 2015

Proceedings of the 25th Edition on Great Lakes Symposium on VLSI

Self Cite

View full text Add to dashboard Cite

Associative memories are an alternative to classical indexed memories that are capable of retrieving a message previously stored when an incomplete version of this message is presented. Recently a new model of associative memory based on binary neurons and binary links has been proposed. This model named Clustered Neural Network (CNN) offers large storage diversity (number of messages stored) and fast message retrieval when implemented in hardware. The performance of this model drops when the stored message distribution is non-uniform. In this paper, we enhance the CNN model to support non-uniform message distribution by adding features of Restricted Boltzmann Machines. In addition, we present a fully parallel hardware design of the model. The proposed implementation multiplies the performance (diversity) of Clustered Neural Networks by a factor of 3 with an increase of complexity of 40%.

show abstract

Section: Complexity Analysismentioning

confidence: 99%

Section: Complexity Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Restricted Clustered Neural Network for Storing Real Data

Danilo

Coussy

Conde-Canencia

et al. 2015

Proceedings of the 25th Edition on Great Lakes Symposium on VLSI

Self Cite

View full text Add to dashboard Cite

show abstract

“…This model, also referred to as the GB model or clustered cliques networks (CCNs), is fundamental in information theory (Gripon & Berrou, 2012) and bears similarity to the Willshaw-type model (Willshaw, Buneman, & Longuet-Higgins, 1969), where sparse patterns and binary connections are considered. These models have been further developed in the literature (Aliabadi, Berrou, Gripon, & Jiang, 2014;Boguslawski, Gripon, Seguin, & Heitzmann, 2014;Jarollahi, Onizawa, Gripon, & Gross, 2014;Jarollahi, Gripon, Onizawa, & Gross, 2015;Jiang, Marques, Kirsch, & Berrou, 2015;Jiang, Gripon, Berrou, & Rabbat, 2016;Mofrad, Ferdosi, Parker, & Tadayon, 2015;Mofrad, Parker, Ferdosi, & Tadayon, 2016;Mofrad & Parker, 2017;Berrou & Kim-Dufor, 2018) and used in many applications, such as solving feature correspondence problems (Aboudib, Gripon, & Coppin, 2016), devising low-power, contentaddressable memory (Jarollahi et al, 2015), oriented edge detection in image (Danilo et al, 2015), image classification with convolutional neural networks (Hacene, Gripon, Farrugia, Arzel, & Jezequel, 2019), and finding all matches of a probe in a database (Hacene, Gripon, Farrugia, Arzel, & Jezequel, 2017), to mention a few. Furthermore, they were implemented on a general-purpose graphical processing unit (GPU) (Yao, Gripon, & Rabbat, 2014), in 65-nm CMOS (Larras, Chollet, Lahuec, Seguin, & Arzel, 2018), and in distributed smart sensor architectures (Larras & Frappé, 2020).…”

Section: Introductionmentioning

confidence: 99%

On Neural Associative Memory Structures: Storage and Retrieval of Sequences in a Chain of Tournaments

Mofrad

Yazidi

et al. 2021

Neural Computation

View full text Add to dashboard Cite

Associative memories enjoy many interesting properties in terms of error correction capabilities, robustness to noise, storage capacity, and retrieval performance, and their usage spans over a large set of applications. In this letter, we investigate and extend tournament-based neural networks, originally proposed by Jiang, Gripon, Berrou, and Rabbat (2016), a novel sequence storage associative memory architecture with high memory efficiency and accurate sequence retrieval. We propose a more general method for learning the sequences, which we call feedback tournament-based neural networks. The retrieval process is also extended to both directions: forward and backward—in other words, any large-enough segment of a sequence can produce the whole sequence. Furthermore, two retrieval algorithms, cache-winner and explore-winner, are introduced to increase the retrieval performance. Through simulation results, we shed light on the strengths and weaknesses of each algorithm.

show abstract

“…Although typical applications of these connectionist models include image recognition and recovery, data analysis, control, inference and prediction (Danilo et al, 2015;Kareem and Jantan, 2011;Lou and Cui, 2007;Mu et al, 2006;Nazari et al, 2014;Štanclová and Zavoral, 2005), the associative memories have lately emerged as useful classifiers for a large variety of problems in data mining and computational intelligence (AldapePérez et al, 2012(AldapePérez et al, , 2015Sharma et al, 2008;Uriarte-Arcia et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Associative learning on imbalanced environments: An empirical study

Cleofas-Sánchez

Sánchez

García

et al. 2016

Expert Systems with Applications

View full text Add to dashboard Cite

Associative memories have emerged as a powerful computational neural network model for several pattern classification problems. Like most traditional classifiers, these models assume that the classes share similar prior probabilities. However, in many real-life applications the ratios of prior probabilities between classes are extremely skewed. Although the literature has provided numerous studies that examine the performance degradation of renowned classifiers on different imbalanced scenarios, so far this effect has not been supported by a thorough empirical study in the context of associative memories. In this paper, we fix our attention on the applicability of the associative neural networks to the classification of imbalanced data. The key questions here addressed are whether these models perform better, the same or worse than other popular classifiers, how the level of imbalance affects their performance, and whether distinct resampling strategies produce a different impact on the associative memories. In order to answer these questions and gain further insight into the feasibility and efficiency of the associative memories, a large-scale experimental evaluation with 31 databases, seven classification models and four resampling algorithms is carried out here, along with a non-parametric statistical test to discover any significant differences between each pair of classifiers.

show abstract

Algorithm and implementation of an associative memory for oriented edge detection using improved clustered neural networks

Cited by 7 publications

References 11 publications

Restricted Clustered Neural Network for Storing Real Data

Restricted Clustered Neural Network for Storing Real Data

On Neural Associative Memory Structures: Storage and Retrieval of Sequences in a Chain of Tournaments

Associative learning on imbalanced environments: An empirical study

Contact Info

Product

Resources

About