Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.
2021-06-17 00:00:00 +0000
General
Nowadays new technologies, and especially artificial intelligence, are more
and more established in our society. Big data analysis and machine learning,
two sub-fields of artificial intelligence, are at the core of many recent
breakthroughs in many application fields (e.g., medicine, communication,
finance, ...), including some that are strongly related to our day-to-day life
(e.g., social networks, computers, smartphones, ...). In machine learning,
significant improvements are usually achieved at the price of an increasing
computational complexity and thanks to bigger datasets. Currently, cutting-edge
models built by the most advanced machine learning algorithms typically became
simultaneously very efficient and profitable but also extremely complex. Their
complexity is to such an extent that these models are commonly seen as
black-boxes providing a prediction or a decision which can not be interpreted
or justified. Nevertheless, whether these models are used autonomously or as a
simple decision-making support tool, they are already being used in machine
learning applications where health and human life are at stake. Therefore, it
appears to be an obvious necessity not to blindly believe everything coming out
of those models without a detailed understanding of their predictions or
decisions. Accordingly, this thesis aims at improving the interpretability of
models built by a specific family of machine learning algorithms, the so-called
tree-based methods. Several mechanisms have been proposed to interpret these
models and we aim along this thesis to improve their understanding, study their
properties, and define their limitations.
2021-06-17 00:00:00 +0000
Pathology
In this work we explore the information processing inside neural networks
using logistic regression probes \cite{probes} and the saturation metric
\cite{featurespace_saturation}. We show that problem difficulty and neural
network capacity affect the predictive performance in an antagonistic manner,
opening the possibility of detecting over- and under-parameterization of neural
networks for a given task. We further show that the observed effects are
independent from previously reported pathological patterns like the ``tail
pattern'' described in \cite{featurespace_saturation}. Finally we are able to
show that saturation patterns converge early during training, allowing for a
quicker cycle time during analysis
2021-06-17 00:00:00 +0000
General
The expanding usage of complex machine learning methods like deep learning
has led to an explosion in human activity recognition, particularly applied to
health. In particular, as part of a larger body sensor network system, face and
full-body analysis is becoming increasingly common for evaluating health
status. However, complex models which handle private and sometimes protected
data, raise concerns about the potential leak of identifiable data. In this
work, we focus on the case of a deep network model trained on images of
individual faces. Full-face video recordings taken from 493 individuals
undergoing an eye-tracking based evaluation of neurological function were used.
Outputs, gradients, intermediate layer outputs, loss, and labels were used as
inputs for a deep network with an added support vector machine emission layer
to recognize membership in the training data. The inference attack method and
associated mathematical analysis indicate that there is a low likelihood of
unintended memorization of facial features in the deep learning model. In this
study, it is showed that the named model preserves the integrity of training
data with reasonable confidence. The same process can be implemented in similar
conditions for different models.
2021-06-17 00:00:00 +0000
General
Vaccines are an important public health measure, but vaccine hesitancy and
refusal can create clusters of low vaccine coverage and reduce the
effectiveness of vaccination programs. Social media provides an opportunity to
estimate emerging risks to vaccine acceptance by including geographical
location and detailing vaccine-related concerns. Methods for classifying social
media posts, such as vaccine-related tweets, use language models (LMs) trained
on general domain text. However, challenges to measuring vaccine sentiment at
scale arise from the absence of tonal stress and gestural cues and may not
always have additional information about the user, e.g., past tweets or social
connections. Another challenge in LMs is the lack of commonsense knowledge that
are apparent in users metadata, i.e., emoticons, positive and negative words
etc. In this study, to classify vaccine sentiment tweets with limited
information, we present a novel end-to-end framework consisting of
interconnected components that use domain-specific LM trained on
vaccine-related tweets and models commonsense knowledge into a bidirectional
gated recurrent network (CK-BiGRU) with context-aware attention. We further
leverage syntactical, user metadata and sentiment information to capture the
sentiment of a tweet. We experimented using two popular vaccine-related Twitter
datasets and demonstrate that our proposed approach outperforms
state-of-the-art models in identifying pro-vaccine, anti-vaccine and neutral
tweets.
2021-06-17 00:00:00 +0000
General
Analyzing the relation between intelligence and neural activity is of the
utmost importance in understanding the working principles of the human brain in
health and disease. In existing literature, functional brain connectomes have
been used successfully to predict cognitive measures such as intelligence
quotient (IQ) scores in both healthy and disordered cohorts using machine
learning models. However, existing methods resort to flattening the brain
connectome (i.e., graph) through vectorization which overlooks its topological
properties. To address this limitation and inspired from the emerging graph
neural networks (GNNs), we design a novel regression GNN model (namely RegGNN)
for predicting IQ scores from brain connectivity. On top of that, we introduce
a novel, fully modular sample selection method to select the best samples to
learn from for our target prediction task. However, since such deep learning
architectures are computationally expensive to train, we further propose a
\emph{learning-based sample selection} method that learns how to choose the
training samples with the highest expected predictive power on unseen samples.
For this, we capitalize on the fact that connectomes (i.e., their adjacency
matrices) lie in the symmetric positive definite (SPD) matrix cone. Our results
on full-scale and verbal IQ prediction outperforms comparison methods in autism
spectrum disorder cohorts and achieves a competitive performance for
neurotypical subjects using 3-fold cross-validation. Furthermore, we show that
our sample selection approach generalizes to other learning-based methods,
which shows its usefulness beyond our GNN architecture.
2021-06-17 00:00:00 +0000
General
The solution to prevent maternal complications are known and preventable by
trained health professionals. But in countries like Ethiopia where the patient
to physician ratio is 1 doctor to 1000 patients, maternal mortality and
morbidity rate is high. To fill the gap of highly trained health professionals,
Ethiopia introduced health extension programs. Task shifting to health
extension workers (HEWs) contributed in decreasing mortality and morbidity rate
in Ethiopia. Knowledge-gap has been one of the major challenges to HEWs. The
reasons are trainings are not given in regular manner, there is no midwife,
gynecologists or doctors around for consultation, and all guidelines are
paper-based which are easily exposed to damage. In this paper, we describe the
design and implementation of a web-based expert system for maternal care. We
only targeted the major 10 diseases and complication of maternal health issues
seen in Sub-Saharan Africa. The expert system can be accessed through the use
of web browsers from computers as well as smart phones. Forward chaining
rule-based expert system is used in order to give suggestions and create a new
knowledge from the knowledge-base. This expert system can be used to train HEWs
in the field of maternal health.
Keywords: expert system, maternal care, forward-chaining, rule-based expert
system, PHLIPS
General
Importance measures derived from random forests: characterisation and extension
ArXiv Preprint
Antonio Sutera
2021-06-17
Pathology
Exploring the Properties and Evolution of Neural Network Eigenspaces during Training
ArXiv Preprint
Mats L. Richter Leila Malihi Anne-Kathrin Patricia Windler Ulf Krumnack
2021-06-17
General
Privacy-Preserving Eye-tracking Using Deep Learning
ArXiv Preprint
Salman Seyedi, Zifan Jiang, Allan Levey, Gari D. Clifford
2021-06-17
General
Classifying vaccine sentiment tweets by modelling domain-specific representation and commonsense knowledge into context-aware attentive GRU
ArXiv Preprint
Usman Naseem, Matloob Khushi, Jinman Kim, Adam G. Dunn
2021-06-17
General
Predicting cognitive scores with graph neural networks through sample selection learning
ArXiv Preprint
Martin Hanik, Mehmet Arif Demirtaş, Mohammed Amine Gharsallaoui, Islem Rekik
2021-06-17
General
MatES: Web-based Forward Chaining Expert System for Maternal Care
ArXiv Preprint
Haile Misgna, Moges Ahmed, Anubhav Kumar
2021-06-17
Weekly Summary
Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.