DeepTox: Toxicity prediction using deep learning

Klambauer, Günter; Unterthiner, Thomas; Mayr, Andreas; Hochreiter, Sepp

doi:10.1016/j.toxlet.2017.07.175

Cited by 228 publications

(279 citation statements)

References 0 publications

Supporting

Mentioning

207

Contrasting

Order By: Relevance

“…To improve the generalization of the model and avoid overfitting, we applied an L2 regularization (regularization parameter = 1 × 10 −3 ) that penalized high values in the network's weights and facilitated diffuse weight vectors as solutions. To mitigate the network's internal covariate shift, the h 1 , z, and h 2 layers were formed using scaled exponential linear units (SELUs; Klambauer, Unterthiner, Mayr, & Hochreiter, ). The activation function of these units allows for faster and more robust training, that is, less training epochs to reach convergence, and a strong regularization scheme (Klambauer et al, ).…”

Section: Methodsmentioning

confidence: 99%

“…To mitigate the network's internal covariate shift, the h 1 , z, and h 2 layers were formed using scaled exponential linear units (SELUs; Klambauer, Unterthiner, Mayr, & Hochreiter, ). The activation function of these units allows for faster and more robust training, that is, less training epochs to reach convergence, and a strong regularization scheme (Klambauer et al, ). We initialized the SELU units using the appropriated initializer (Klambauer et al, ).…”

Section: Methodsmentioning

confidence: 99%

“…The activation function of these units allows for faster and more robust training, that is, less training epochs to reach convergence, and a strong regularization scheme (Klambauer et al, ). We initialized the SELU units using the appropriated initializer (Klambauer et al, ). The output layer was formed by linear units initialized with Glorot initialization, also known as Xavier initialization (Glorot & Bengio, ), using weight parameters sampled from a uniform distribution.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Using deep autoencoders to identify abnormal brain structural patterns in neuropsychiatric disorders: A large‐scale multi‐sample study

Pinaya

Mechelli

Sato

2018

Human Brain Mapping

101

View full text Add to dashboard Cite

Machine learning is becoming an increasingly popular approach for investigating spatially distributed and subtle neuroanatomical alterations in brain‐based disorders. However, some machine learning models have been criticized for requiring a large number of cases in each experimental group, and for resembling a “black box” that provides little or no insight into the nature of the data. In this article, we propose an alternative conceptual and practical approach for investigating brain‐based disorders which aim to overcome these limitations. We used an artificial neural network known as “deep autoencoder” to create a normative model using structural magnetic resonance imaging data from 1,113 healthy people. We then used this model to estimate total and regional neuroanatomical deviation in individual patients with schizophrenia and autism spectrum disorder using two independent data sets ( n = 263). We report that the model was able to generate different values of total neuroanatomical deviation for each disease under investigation relative to their control group ( p < .005). Furthermore, the model revealed distinct patterns of neuroanatomical deviations for the two diseases, consistent with the existing neuroimaging literature. We conclude that the deep autoencoder provides a flexible and promising framework for assessing total and regional neuroanatomical deviations in neuropsychiatric populations.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Using deep autoencoders to identify abnormal brain structural patterns in neuropsychiatric disorders: A large‐scale multi‐sample study

Pinaya

Mechelli

Sato

2018

Human Brain Mapping

101

View full text Add to dashboard Cite

show abstract

“…The activation operations should provide dierent types of nonlinearities in the neural networks to solve Multiclass Classication problems. In general, there are two types of activation functions, including smooth nonlinear functions, such as Sigmoid, Tanh, Exponential Linear Units (ELU) [13], Scaled Exponential Linear Units (SELU) [14], etc., and smooth continuous functions, such as Rectied linear unit (ReLU) [15], Concatenated Rectied Linear Units (CReLu) [16], etc. We nd that for classifying synthesis ows, the activation functions with nonlinearities perform better, such SELU and Tanh.…”

Section: Cnn Architecture and Trainingmentioning

confidence: 99%

“…Figure 7 includes the comparison of eight dierent activation functions, including ReLU, ReLU6, ELU [13], SELU [14], Softplus, Softsign, Sigmoid and Tanh. We can see that the ELU, SELU, Softsign and Tanh functions outperform the others, and SELU oers the best accuracy for generating delay-driven ows for the 128-bit AES core.…”

Section: Evaluation Of Activation Functionsmentioning

confidence: 99%

Developing synthesis flows without human knowledge

Xiao

Micheli

2018

Proceedings of the 55th Annual Design Automation Conference

View full text Add to dashboard Cite

Design ows are the explicit combinations of design transformations, primarily involved in synthesis, placement and routing processes, to accomplish the design of Integrated Circuits (ICs) and System-on-Chip (SoC). Mostly, the ows are developed based on the knowledge of the experts. However, due to the large search space of design ows and the increasing design complexity, developing Intellectual Property (IP)-specic synthesis ows providing high Quality of Result (QoR) is extremely challenging. This work presents a fully autonomous framework that articially produces design-specic synthesis ows without human guidance and baseline ows, using Convolutional Neural Network (CNN). The demonstrations are made by successfully designing logic synthesis ows of three large scaled designs.

show abstract

Why it is Unfortunate that Linear Machine Learning “Works” so well in Electromechanical Switching of Ferroelectric Thin Films

et al. 2022

View full text Add to dashboard Cite

Machine learning (ML) is relied on for materials spectroscopy. It is challenging to make ML models fail because statistical correlations can mimic the physics without causality. Here, using a benchmark band‐excitation piezoresponse force microscopy polarization spectroscopy (BEPS) dataset the pitfalls of the so‐called “better”, “faster”, and “less‐biased” ML of electromechanical switching are demonstrated and overcome. Using a toy and real experimental dataset, it is demonstrated how linear nontemporal ML methods result in physically reasonable embedding (eigenvalues) while producing nonsensical eigenvectors and generated spectra, promoting misleading interpretations. A new method of unsupervised multimodal hyperspectral analysis of BEPS is demonstrated using long‐short‐term memory (LSTM) β‐variational autoencoders (β‐VAEs) . By including LSTM neurons, the ordinal nature of ferroelectric switching is considered. To improve the interpretability of the latent space, a variational Kullback–Leibler‐divergency regularization is imposed . Finally, regularization scheduling of β as a disentanglement metric is leveraged to reduce user bias. Combining these experiment‐inspired modifications enables the automated detection of ferroelectric switching mechanisms, including a complex two‐step, three‐state one. Ultimately, this work provides a robust ML method for the rapid discovery of electromechanical switching mechanisms in ferroelectrics and is applicable to other multimodal hyperspectral materials spectroscopies.

show abstract

DeepTox: Toxicity prediction using deep learning

Cited by 228 publications

References 0 publications

Using deep autoencoders to identify abnormal brain structural patterns in neuropsychiatric disorders: A large‐scale multi‐sample study

Using deep autoencoders to identify abnormal brain structural patterns in neuropsychiatric disorders: A large‐scale multi‐sample study

Developing synthesis flows without human knowledge

Why it is Unfortunate that Linear Machine Learning “Works” so well in Electromechanical Switching of Ferroelectric Thin Films

Contact Info

Product

Resources

About