activity
20162022
most citedImproving the Expected Improvement Algorithm

39 citations · 154 across the 26 of their papers we have counts for

collaborators
Showing 2018Show all

10 papers · 1 filter

cs.LG2018

Layer Flexible Adaptive Computational Time

Lida Zhang, Abdolghani Ebrahimi, Diego Klabjan

Deep recurrent neural networks perform well on sequence data and are the model of choice. However, it is a daunting task to decide the structure of the networks, i.e. the number of…

stat.ML2018

Unified recurrent neural network for many feature types

Alexander Stec, Diego Klabjan, Jean Utke

There are time series that are amenable to recurrent neural network (RNN) solutions when treated as sequences, but some series, e.g. asynchronous time series, provide a richer vari…

cs.LG2018

Combined convolutional and recurrent neural networks for hierarchical classification of images

Jaehoon Koo, Diego Klabjan, Jean Utke

Deep learning models based on CNNs are predominantly used in image classification tasks. Such approaches, assuming independence of object categories, normally use a CNN as a featur…

stat.ML2018

Nested multi-instance classification

Alexander Stec, Diego Klabjan, Jean Utke

There are classification tasks that take as inputs groups of images rather than single images. In order to address such situations, we introduce a nested multi-instance deep networ…

cs.LG2018

Dynamic Prediction Length for Time Series with Sequence to Sequence Networks

Mark Harmon, Diego Klabjan

Recurrent neural networks and sequence to sequence models require a predetermined length for prediction output length. Our model addresses this by allowing the network to predict a…

stat.ML2018

Forecasting Crime with Deep Learning

Alexander Stec, Diego Klabjan

The objective of this work is to take advantage of deep neural networks in order to make next day crime count predictions in a fine-grain city partition. We make predictions using…