A comparative evaluation of supervised and unsupervised representation learning approaches for anaplastic medulloblastoma differentiation

2015 ◽  
Author(s):  
Angel Cruz-Roa ◽  
John Arevalo ◽  
Ajay Basavanhally ◽  
Anant Madabhushi ◽  
Fabio González
Keyword(s):  
Comparative Evaluation ◽  
Representation Learning ◽  
Learning Approaches ◽  
Anaplastic Medulloblastoma

scholarly journals Efficient Rank-Based Diffusion Process with Assured Convergence

2021 ◽  
Vol 7 (3) ◽  
pp. 49
Author(s):  
Daniel Carlos Guimarães Pedronette ◽  
Lucas Pascotti Valem ◽  
Longin Jan Latecki
Keyword(s):  
Diffusion Process ◽  
Learning Strategies ◽  
State Of The Art ◽  
Representation Learning ◽  
Theoretical Background ◽  
High Dimensional ◽  
Visual Features ◽  
Learning Approaches ◽  
Previous Decade ◽  
Asymptotic Complexity

Visual features and representation learning strategies experienced huge advances in the previous decade, mainly supported by deep learning approaches. However, retrieval tasks are still performed mainly based on traditional pairwise dissimilarity measures, while the learned representations lie on high dimensional manifolds. With the aim of going beyond pairwise analysis, post-processing methods have been proposed to replace pairwise measures by globally defined measures, capable of analyzing collections in terms of the underlying data manifold. The most representative approaches are diffusion and ranked-based methods. While the diffusion approaches can be computationally expensive, the rank-based methods lack theoretical background. In this paper, we propose an efficient Rank-based Diffusion Process which combines both approaches and avoids the drawbacks of each one. The obtained method is capable of efficiently approximating a diffusion process by exploiting rank-based information, while assuring its convergence. The algorithm exhibits very low asymptotic complexity and can be computed regionally, being suitable to outside of dataset queries. An experimental evaluation conducted for image retrieval and person re-ID tasks on diverse datasets demonstrates the effectiveness of the proposed approach with results comparable to the state-of-the-art.

scholarly journals MolTrans: Molecular Interaction Transformer for drug–target interaction prediction

2020 ◽  
Author(s):  
Kexin Huang ◽  
Cao Xiao ◽  
Lucas M Glass ◽  
Jimeng Sun
Keyword(s):  
Molecular Interaction ◽  
Drug Target ◽  
Pattern Mining ◽  
Representation Learning ◽  
Molecular Data ◽  
Supplementary Information ◽  
Biomedical Data ◽  
Learning Approaches ◽  
Real World Data ◽  
Target Interaction

Abstract Motivation Drug–target interaction (DTI) prediction is a foundational task for in-silico drug discovery, which is costly and time-consuming due to the need of experimental search over large drug compound space. Recent years have witnessed promising progress for deep learning in DTI predictions. However, the following challenges are still open: (i) existing molecular representation learning approaches ignore the sub-structural nature of DTI, thus produce results that are less accurate and difficult to explain and (ii) existing methods focus on limited labeled data while ignoring the value of massive unlabeled molecular data. Results We propose a Molecular Interaction Transformer (MolTrans) to address these limitations via: (i) knowledge inspired sub-structural pattern mining algorithm and interaction modeling module for more accurate and interpretable DTI prediction and (ii) an augmented transformer encoder to better extract and capture the semantic relations among sub-structures extracted from massive unlabeled biomedical data. We evaluate MolTrans on real-world data and show it improved DTI prediction performance compared to state-of-the-art baselines. Availability and implementation The model scripts are available at https://github.com/kexinhuang12345/moltrans. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Deep representation learning improves prediction of LacI-mediated transcriptional repression

2021 ◽  
Vol 118 (27) ◽  
pp. e2022838118
Author(s):  
Alexander S. Garruss ◽  
Katherine M. Collins ◽  
George M. Church
Keyword(s):  
Escherichia Coli ◽  
Protein Function ◽  
Transcriptional Repression ◽  
Pearson Correlation ◽  
Representation Learning ◽  
Lac Repressor ◽  
Learning Approaches ◽  
Sequencing Technology ◽  
Massive Scale ◽  
Evolutionary Aspects

Recent progress in DNA synthesis and sequencing technology has enabled systematic studies of protein function at a massive scale. We explore a deep mutational scanning study that measured the transcriptional repression function of 43,669 variants of the Escherichia coli LacI protein. We analyze structural and evolutionary aspects that relate to how the function of this protein is maintained, including an in-depth look at the C-terminal domain. We develop a deep neural network to predict transcriptional repression mediated by the lac repressor of Escherichia coli using experimental measurements of variant function. When measured across 10 separate training and validation splits using 5,009 single mutations of the lac repressor, our best-performing model achieved a median Pearson correlation of 0.79, exceeding any previous model. We demonstrate that deep representation learning approaches, first trained in an unsupervised manner across millions of diverse proteins, can be fine-tuned in a supervised fashion using lac repressor experimental datasets to more effectively predict a variant’s effect on repression. These findings suggest a deep representation learning model may improve the prediction of other important properties of proteins.

scholarly journals PENGARUH PENDEKATAN MULTI REPRESENTASI TERHADAP HASIL BELAJAR FISIKA DITINJAU DARI MOTIVASI BELAJAR PESERTA DIDIK

2018 ◽  
Vol 4 (1) ◽  
Author(s):  
Aris Doyan ◽  
Muhammad Taufik ◽  
Raudah Anjani
Keyword(s):  
Learning Outcomes ◽  
Sampling Technique ◽  
Representation Learning ◽  
Learning Motivation ◽  
Choice Test ◽  
Learning Approach ◽  
Learning Approaches ◽  
Validity Data ◽  
Physics Learning ◽  
Significance Level

The purpose of this study is determine the effect of multi representation learning approaches to physics learning, the effect of students learning motivation on physics learning, and the interaction between the multi representational learning approach and the students learning motivation toward the learning outcomes of physics. This type of research is quasi experiment with non-equivalent group design. Sampling using purposive sampling technique, so that obtained class XI MIA 1 as experiment class and class XI MIA 2 as control class. The research instrument is a multiple choice test for physics learning result of 25 questions that have been tested for validity, reliability, level of difficulty, and different power of problems. The learning data of the two classes is normally distributed. Based on the homogeneity data obtained both homogeneous. Instrument to measure motivation to learn in the form of motivation questionnaire that has been tested by the expert team of validity. Data were analyzed by two-way ANOVA test. Result of data analysis show Ftable at 5% significance level equal to 3,97. Test the effect of multi representation learning approaches to physics learning equal to Fcount (8,857) > Ftable (3,97). Test the effect of students learning motivation on physics learning equal to Fcount (9.00) > Ftable (3,97). Test  the interaction between the multi representational learning approach and the students learning motivation toward the learning outcomes of physics equal to Fcount (2.00) < Ftable (3,97). Based on these facts it can be concluded that there is influence of multi representation learning approach to physics learning result, there is influence of learning motivation learners to physics learning result, and there is no interaction between multi-representation learning approach with learning motivation of learners toward physics learning result.Keywords: multi representation learning approach, physics learning result, learning motivation

scholarly journals Standard machine learning approaches outperform deep representation learning on phenotype prediction from transcriptomics data

2020 ◽  
Vol 21 (1) ◽  
Author(s):  
Aaron M. Smith ◽  
Jonathan R. Walsh ◽  
John Long ◽  
Craig B. Davis ◽  
Peter Henstock ◽  
...  
Keyword(s):  
Machine Learning ◽  
Representation Learning ◽  
Learning Approaches ◽  
Phenotype Prediction ◽  
Transcriptomics Data

scholarly journals MACHINE LEARNING FOR SEA ICE MONITORING FROM SATELLITES

2019 ◽  
Vol XLII-2/W16 ◽  
pp. 83-89
Author(s):  
C. O. Dumitru ◽  
V. Andrei ◽  
G. Schwarz ◽  
M. Datcu
Keyword(s):  
Machine Learning ◽  
Sea Ice ◽  
Weather Conditions ◽  
Representation Learning ◽  
Image Understanding ◽  
Machine Learning Techniques ◽  
Polar Regions ◽  
Learning Approaches ◽  
Automated Processing ◽  
Modern Machine

<p><strong>Abstract.</strong> Today, radar imaging from space allows continuous and wide-area sea ice monitoring under nearly all weather conditions. To this end, we applied modern machine learning techniques to produce ice-describing semantic maps of the polar regions of the Earth. Time series of these maps can then be exploited for local and regional change maps of selected areas. What we expect, however, are fully-automated unsupervised routine classifications of sea ice regions that are needed for the rapid and reliable monitoring of shipping routes, drifting and disintegrating icebergs, snowfall and melting on ice, and other dynamic climate change indicators. Therefore, we designed and implemented an automated processing chain that analyses and interprets the specific ice-related content of high-resolution synthetic aperture radar (SAR) images. We trained this system with selected images covering various use cases allowing us to interpret these images with modern machine learning approaches. In the following, we describe a system comprising representation learning, variational inference, and auto-encoders. Test runs have already demonstrated its usefulness and stability that can pave the way towards future artificial intelligence systems extending, for instance, the current capabilities of traditional image analysis by including content-related image understanding.</p>

scholarly journals Feature Hashing for Network Representation Learning

2018 ◽  
Author(s):  
Qixiang Wang ◽  
Shanfeng Wang ◽  
Maoguo Gong ◽  
Yue Wu
Keyword(s):  
Link Prediction ◽  
Feature Space ◽  
Representation Learning ◽  
Learning Approaches ◽  
Network Representation ◽  
Proximity Matrix ◽  
Low Dimensional ◽  
Vector Representations ◽  
Feature Hashing ◽  
Node Embeddings

The goal of network representation learning is to embed nodes so as to encode the proximity structures of a graph into a continuous low-dimensional feature space. In this paper, we propose a novel algorithm called node2hash based on feature hashing for generating node embeddings. This approach follows the encoder-decoder framework. There are two main mapping functions in this framework. The first is an encoder to map each node into high-dimensional vectors. The second is a decoder to hash these vectors into a lower dimensional feature space. More specifically, we firstly derive a proximity measurement called expected distance as target which combines position distribution and co-occurrence statistics of nodes over random walks so as to build a proximity matrix, then introduce a set of T different hash functions into feature hashing to generate uniformly distributed vector representations of nodes from the proximity matrix. Compared with the existing state-of-the-art network representation learning approaches, node2hash shows a competitive performance on multi-class node classification and link prediction tasks on three real-world networks from various domains.

Unified Representation Learning Approaches

2021 ◽  
pp. 143-152
Author(s):  
Nada Lavrač ◽  
Vid Podpečan ◽  
Marko Robnik-Šikonja
Keyword(s):  
Representation Learning ◽  
Learning Approaches
Sign in / Sign up

Export Citation Format

Share Document