Alert button
Picture for Adel Ardalan

Adel Ardalan

Alert button

Recurrent neural network models for working memory of continuous variables: activity manifolds, connectivity patterns, and dynamic codes

Nov 01, 2021
Christopher J. Cueva, Adel Ardalan, Misha Tsodyks, Ning Qian

Figure 1 for Recurrent neural network models for working memory of continuous variables: activity manifolds, connectivity patterns, and dynamic codes
Figure 2 for Recurrent neural network models for working memory of continuous variables: activity manifolds, connectivity patterns, and dynamic codes
Figure 3 for Recurrent neural network models for working memory of continuous variables: activity manifolds, connectivity patterns, and dynamic codes
Figure 4 for Recurrent neural network models for working memory of continuous variables: activity manifolds, connectivity patterns, and dynamic codes
Viaarxiv icon

In-RDBMS Hardware Acceleration of Advanced Analytics

Sep 18, 2018
Divya Mahajan, Joon Kyung Kim, Jacob Sacks, Adel Ardalan, Arun Kumar, Hadi Esmaeilzadeh

Figure 1 for In-RDBMS Hardware Acceleration of Advanced Analytics
Figure 2 for In-RDBMS Hardware Acceleration of Advanced Analytics
Figure 3 for In-RDBMS Hardware Acceleration of Advanced Analytics
Figure 4 for In-RDBMS Hardware Acceleration of Advanced Analytics
Viaarxiv icon

Applications of Machine Learning Methods to Quantifying Phenotypic Traits that Distinguish the Wild Type from the Mutant Arabidopsis Thaliana Seedlings during Root Gravitropism

Aug 31, 2010
Hesam T. Dashti, Jernej Tonejc, Adel Ardalan, Alireza F. Siahpirani, Sabrina Guettes, Zohreh Sharif, Liya Wang, Amir H. Assadi

Figure 1 for Applications of Machine Learning Methods to Quantifying Phenotypic Traits that Distinguish the Wild Type from the Mutant Arabidopsis Thaliana Seedlings during Root Gravitropism
Figure 2 for Applications of Machine Learning Methods to Quantifying Phenotypic Traits that Distinguish the Wild Type from the Mutant Arabidopsis Thaliana Seedlings during Root Gravitropism
Figure 3 for Applications of Machine Learning Methods to Quantifying Phenotypic Traits that Distinguish the Wild Type from the Mutant Arabidopsis Thaliana Seedlings during Root Gravitropism
Figure 4 for Applications of Machine Learning Methods to Quantifying Phenotypic Traits that Distinguish the Wild Type from the Mutant Arabidopsis Thaliana Seedlings during Root Gravitropism
Viaarxiv icon

Pattern Recognition in Collective Cognitive Systems: Hybrid Human-Machine Learning (HHML) By Heterogeneous Ensembles

Aug 31, 2010
Hesam T. Dashti, Adel Ardalan, Alireza F. Siahpirani, Jernej Tonejc, Ioan V. Uilecan, Tiago Simas, Bruno Miranda, Rita Ribeiro, Liya Wang, Amir H. Assadi

Figure 1 for Pattern Recognition in Collective Cognitive Systems: Hybrid Human-Machine Learning (HHML) By Heterogeneous Ensembles
Figure 2 for Pattern Recognition in Collective Cognitive Systems: Hybrid Human-Machine Learning (HHML) By Heterogeneous Ensembles
Figure 3 for Pattern Recognition in Collective Cognitive Systems: Hybrid Human-Machine Learning (HHML) By Heterogeneous Ensembles
Figure 4 for Pattern Recognition in Collective Cognitive Systems: Hybrid Human-Machine Learning (HHML) By Heterogeneous Ensembles
Viaarxiv icon