LIVIVO - Suchergebnisse -

Suchergebnis

Treffer 1 - 10 von insgesamt 212

Suchoptionen

Buch ; Online: Unnormalized Variational Bayes

Saremi, Saeed

2020

Abstract: We unify empirical Bayes and variational Bayes for approximating unnormalized densities. This framework, named unnormalized variational Bayes (UVB), is based on formulating a latent variable model for the random variable $Y=X+N(0,\sigma^2 I_d)$ and using ...

Abstract	We unify empirical Bayes and variational Bayes for approximating unnormalized densities. This framework, named unnormalized variational Bayes (UVB), is based on formulating a latent variable model for the random variable $Y=X+N(0,\sigma^2 I_d)$ and using the evidence lower bound (ELBO), computed by a variational autoencoder, as a parametrization of the energy function of $Y$ which is then used to estimate $X$ with the empirical Bayes least-squares estimator. In this intriguing setup, the $\textit{gradient}$ of the ELBO with respect to noisy inputs plays the central role in learning the energy function. Empirically, we demonstrate that UVB has a higher capacity to approximate energy functions than the parametrization with MLPs as done in neural empirical Bayes (DEEN). We especially showcase $\sigma=1$, where the differences between UVB and DEEN become visible and qualitative in the denoising experiments. For this high level of noise, the distribution of $Y$ is very smoothed and we demonstrate that one can traverse in a single run $-$ without a restart $-$ all MNIST classes in a variety of styles via walk-jump sampling with a fast-mixing Langevin MCMC sampler. We finish by probing the encoder/decoder of the trained models and confirm UVB $\neq$ VAE. Comment: Submitted to Journal of Machine Learning Research
Schlagwörter	Statistics - Machine Learning ; Computer Science - Machine Learning
Thema/Rubrik (Code)	670
Erscheinungsdatum	2020-07-29
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Buch ; Online: Learning and Inference in Imaginary Noise Models

Saremi, Saeed

2020

Abstract: Inspired by recent developments in learning smoothed densities with empirical Bayes, we study variational autoencoders with a decoder that is tailored for the random variable $Y=X+N(0,\sigma^2 I_d)$. A notion of smoothed variational inference emerges ... ...

Abstract	Inspired by recent developments in learning smoothed densities with empirical Bayes, we study variational autoencoders with a decoder that is tailored for the random variable $Y=X+N(0,\sigma^2 I_d)$. A notion of smoothed variational inference emerges where the smoothing is implicitly enforced by the noise model of the decoder; "implicit", since during training the encoder only sees clean samples. This is the concept of imaginary noise model, where the noise model dictates the functional form of the variational lower bound $\mathcal{L}(\sigma)$, but the noisy data are never seen during learning. The model is named $\sigma$-VAE. We prove that all $\sigma$-VAEs are equivalent to each other via a simple $\beta$-VAE expansion: $\mathcal{L}(\sigma_2) \equiv \mathcal{L}(\sigma_1,\beta)$, where $\beta=\sigma_2^2/\sigma_1^2$. We prove a similar result for the Laplace distribution in exponential families. Empirically, we report an intriguing power law $\mathcal{D}_{\rm KL} \sim \sigma^{-\nu}$ for the learned models and we study the inference in the $\sigma$-VAE for unseen noisy data. The experiments were performed on MNIST, where we show that quite remarkably the model can make reasonable inferences on extremely noisy samples even though it has not seen any during training. The vanilla VAE completely breaks down in this regime. We finish with a hypothesis (the XYZ hypothesis) on the findings here.
Schlagwörter	Statistics - Machine Learning ; Computer Science - Machine Learning
Thema/Rubrik (Code)	006
Erscheinungsdatum	2020-05-18
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Buch ; Online: On approximating $\nabla f$ with neural networks

Saremi, Saeed

2019

Abstract: Consider a feedforward neural network $\psi: \mathbb{R}^d\rightarrow \mathbb{R}^d$ such that $\psi\approx \nabla f$, where $f:\mathbb{R}^d \rightarrow \mathbb{R}$ is a smooth function, therefore $\psi$ must satisfy $\partial_j \psi_i = \partial_i \psi_j$ ...

Abstract	Consider a feedforward neural network $\psi: \mathbb{R}^d\rightarrow \mathbb{R}^d$ such that $\psi\approx \nabla f$, where $f:\mathbb{R}^d \rightarrow \mathbb{R}$ is a smooth function, therefore $\psi$ must satisfy $\partial_j \psi_i = \partial_i \psi_j$ pointwise. We prove a theorem that a $\psi$ network with more than one hidden layer can only represent one feature in its first hidden layer; this is a dramatic departure from the well-known results for one hidden layer. The proof of the theorem is straightforward, where two backward paths and a weight-tying matrix play the key roles. We then present the alternative, the implicit parametrization, where the neural network is $\phi: \mathbb{R}^d \rightarrow \mathbb{R}$ and $\nabla \phi \approx \nabla f$; in addition, a "soft analysis" of $\nabla \phi$ gives a dual perspective on the theorem. Throughout, we come back to recent probabilistic models that are formulated as $\nabla \phi \approx \nabla f$, and conclude with a critique of denoising autoencoders. Comment: 10 pages
Schlagwörter	Statistics - Machine Learning ; Computer Science - Machine Learning
Thema/Rubrik (Code)	519
Erscheinungsdatum	2019-10-28
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Buch ; Online: Chain of Log-Concave Markov Chains

Saremi, Saeed / Park, Ji Won / Bach, Francis

2023

Abstract: We introduce a theoretical framework for sampling from unnormalized densities based on a smoothing scheme that uses an isotropic Gaussian kernel with a single fixed noise scale. We prove one can decompose sampling from a density (minimal assumptions made ...

Abstract	We introduce a theoretical framework for sampling from unnormalized densities based on a smoothing scheme that uses an isotropic Gaussian kernel with a single fixed noise scale. We prove one can decompose sampling from a density (minimal assumptions made on the density) into a sequence of sampling from log-concave conditional densities via accumulation of noisy measurements with equal noise levels. Our construction is unique in that it keeps track of a history of samples, making it non-Markovian as a whole, but it is lightweight algorithmically as the history only shows up in the form of a running empirical mean of samples. Our sampling algorithm generalizes walk-jump sampling (Saremi & Hyv\"arinen, 2019). The "walk" phase becomes a (non-Markovian) chain of (log-concave) Markov chains. The "jump" from the accumulated measurements is obtained by empirical Bayes. We study our sampling algorithm quantitatively using the 2-Wasserstein metric and compare it with various Langevin MCMC algorithms. We also report a remarkable capacity of our algorithm to "tunnel" between modes of a distribution.
Schlagwörter	Statistics - Machine Learning ; Computer Science - Machine Learning ; Statistics - Computation
Erscheinungsdatum	2023-05-30
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Buch ; Online: Multimeasurement Generative Models

Saremi, Saeed / Srivastava, Rupesh Kumar

2021

Abstract: We formally map the problem of sampling from an unknown distribution with a density in $\mathbb{R}^d$ to the problem of learning and sampling a smoother density in $\mathbb{R}^{Md}$ obtained by convolution with a fixed factorial kernel: the new density ... ...

Abstract	We formally map the problem of sampling from an unknown distribution with a density in $\mathbb{R}^d$ to the problem of learning and sampling a smoother density in $\mathbb{R}^{Md}$ obtained by convolution with a fixed factorial kernel: the new density is referred to as M-density and the kernel as multimeasurement noise model (MNM). The M-density in $\mathbb{R}^{Md}$ is smoother than the original density in $\mathbb{R}^d$, easier to learn and sample from, yet for large $M$ the two problems are mathematically equivalent since clean data can be estimated exactly given a multimeasurement noisy observation using the Bayes estimator. To formulate the problem, we derive the Bayes estimator for Poisson and Gaussian MNMs in closed form in terms of the unnormalized M-density. This leads to a simple least-squares objective for learning parametric energy and score functions. We present various parametrization schemes of interest including one in which studying Gaussian M-densities directly leads to multidenoising autoencoders--this is the first theoretical connection made between denoising autoencoders and empirical Bayes in the literature. Samples in $\mathbb{R}^d$ are obtained by walk-jump sampling (Saremi & Hyvarinen, 2019) via underdamped Langevin MCMC (walk) to sample from M-density and the multimeasurement Bayes estimation (jump). We study permutation invariant Gaussian M-densities on MNIST, CIFAR-10, and FFHQ-256 datasets, and demonstrate the effectiveness of this framework for realizing fast-mixing stable Markov chains in high dimensions. Comment: Our code is publicly available at https://github.com/nnaisense/mems
Schlagwörter	Statistics - Machine Learning ; Computer Science - Machine Learning
Thema/Rubrik (Code)	519
Erscheinungsdatum	2021-12-17
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Artikel ; Online: Induction of apoptosis and suppression of Ras gene expression in MCF human breast cancer cells.

Saremi, Sadegh / Kolahi, Maryam / Tabandeh, Mohammad Reza / Hashemitabar, Mahmoud

Journal of cancer research and therapeutics

2022 Band 18, Heft 4, Seite(n) 1052–1060

Abstract: Breast cancer is the leading invasive cancer in women globally. This study aimed at evaluating the anti-apoptotic activity of p-Coumaric acid (PCA) on MCF-7 breast cancer cell line. Experiments were conducted in which the MCF-7 cell line was treated with ...

Abstract	Breast cancer is the leading invasive cancer in women globally. This study aimed at evaluating the anti-apoptotic activity of p-Coumaric acid (PCA) on MCF-7 breast cancer cell line. Experiments were conducted in which the MCF-7 cell line was treated with PCA. which showed decreased cell viability, increased lactate dehydrogenase activity, and caspase-3 activation. The results were evaluated with real-time polymerase chain reaction which revealed that PCA reduced the amount of H-Ras and K-Ras transcript in MCF-7 breast cancer cells. In the presence of PCA there was a significant increase in the levels of mRNA gene Bax and late apoptotic cells which was dose dependent. It also retarded the relative expression of antiapoptotic gene, Bcl2 in treated cells. The results suggest that PCA exhibits anti-cancer properties against MCF-7 cells. PCA inhibited the growth of MCF7 cell. The optimum concentration of PCA was 75-150 mM. PCA can inhibit the growth of MCF-7 cells by reducing Ras expression and inducing cell apoptosis. Our results suggest that PCA could prove valuable in the search for possible inhibitors of Ras oncogene functionality and gain further support for its potential utilization in the treatment of patients with breast cancer. PCA is safe and could complement current treatments employed for the disease.
Mesh-Begriff(e)	Apoptosis/genetics ; Breast Neoplasms/drug therapy ; Breast Neoplasms/genetics ; Breast Neoplasms/metabolism ; Caspase 3/metabolism ; Cell Proliferation/genetics ; Female ; Gene Expression ; Genes, ras ; Humans ; Lactate Dehydrogenases/genetics ; MCF-7 Cells ; RNA, Messenger/metabolism ; bcl-2-Associated X Protein/genetics
Chemische Substanzen	RNA, Messenger ; bcl-2-Associated X Protein ; Lactate Dehydrogenases (EC 1.1.-) ; Caspase 3 (EC 3.4.22.-)
Sprache	Englisch
Erscheinungsdatum	2022-09-16
Erscheinungsland	India
Dokumenttyp	Journal Article
ZDB-ID	2187633-2
ISSN	1998-4138 ; 0973-1482
ISSN (online)	1998-4138
ISSN	0973-1482
DOI	10.4103/jcrt.JCRT_624_20
Datenquelle	MEDical Literature Analysis and Retrieval System OnLINE

Zusatzmaterialien

Über subito bestellen

Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

Details ▾
- Kostenpflichtig bestellen

Buch ; Online: Provable Robust Classification via Learned Smoothed Densities

Saremi, Saeed / Srivastava, Rupesh

2020

Abstract: Smoothing classifiers and probability density functions with Gaussian kernels appear unrelated, but in this work, they are unified for the problem of robust classification. The key building block is approximating the $\textit{energy function}$ of the ... ...

Abstract	Smoothing classifiers and probability density functions with Gaussian kernels appear unrelated, but in this work, they are unified for the problem of robust classification. The key building block is approximating the $\textit{energy function}$ of the random variable $Y=X+N(0,\sigma^2 I_d)$ with a neural network which we use to formulate the problem of robust classification in terms of $\widehat{x}(Y)$, the $\textit{Bayes estimator}$ of $X$ given the noisy measurements $Y$. We introduce $\textit{empirical Bayes smoothed classifiers}$ within the framework of $\textit{randomized smoothing}$ and study it theoretically for the two-class linear classifier, where we show one can improve their robustness above $\textit{the margin}$. We test the theory on MNIST and we show that with a learned smoothed energy function and a linear classifier we can achieve provable $\ell_2$ robust accuracies that are competitive with empirical defenses. This setup can be significantly improved by $\textit{learning}$ empirical Bayes smoothed classifiers with adversarial training and on MNIST we show that we can achieve provable robust accuracies higher than the state-of-the-art empirical defenses in a range of radii. We discuss some fundamental challenges of randomized smoothing based on a geometric interpretation due to concentration of Gaussians in high dimensions, and we finish the paper with a proposal for using walk-jump sampling, itself based on learned smoothed densities, for robust classification. Comment: 24 pages, 6 figures
Schlagwörter	Statistics - Machine Learning ; Computer Science - Machine Learning ; Mathematics - Optimization and Control
Thema/Rubrik (Code)	006 ; 519
Erscheinungsdatum	2020-05-09
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Artikel: Assessment of Standard Operating Procedures (SOPs) Preparing Hygienic Condition in the Blood Donation Centers during the Outbreak of COVID-19.

Mohammadi, Saeed / Tabatabaei Yazdi, Seyed Morteza / Balagholi, Sahar / Saremi, Saeid / Dabbaghi, Rasul / Ferdowsi, Shirin / Eshghi, Peyman

International journal of hematology-oncology and stem cell research

2023 Band 17, Heft 3, Seite(n) 167–176

Abstract: Background: ...

Abstract	Background:
Sprache	Englisch
Erscheinungsdatum	2023-09-08
Erscheinungsland	Iran
Dokumenttyp	Journal Article
ZDB-ID	2652853-8
ISSN	2008-2207 ; 2008-3009
ISSN (online)	2008-2207
ISSN	2008-3009
DOI	10.18502/ijhoscr.v17i3.13306
Datenquelle	MEDical Literature Analysis and Retrieval System OnLINE

Zusatzmaterialien

Über subito bestellen

Details ▾
- Kostenpflichtig bestellen

Buch ; Online: Automatic design of novel potential 3CL$^{\text{pro}}$ and PL$^{\text{pro}}$ inhibitors

Atkinson, Timothy / Saremi, Saeed / Gomez, Faustino / Masci, Jonathan

2021

Abstract: With the goal of designing novel inhibitors for SARS-CoV-1 and SARS-CoV-2, we propose the general molecule optimization framework, Molecular Neural Assay Search (MONAS), consisting of three components: a property predictor which identifies molecules with ...

Abstract	With the goal of designing novel inhibitors for SARS-CoV-1 and SARS-CoV-2, we propose the general molecule optimization framework, Molecular Neural Assay Search (MONAS), consisting of three components: a property predictor which identifies molecules with specific desirable properties, an energy model which approximates the statistical similarity of a given molecule to known training molecules, and a molecule search method. In this work, these components are instantiated with graph neural networks (GNNs), Deep Energy Estimator Networks (DEEN) and Monte Carlo tree search (MCTS), respectively. This implementation is used to identify 120K molecules (out of 40-million explored) which the GNN determined to be likely SARS-CoV-1 inhibitors, and, at the same time, are statistically close to the dataset used to train the GNN.
Schlagwörter	Computer Science - Machine Learning ; Computer Science - Artificial Intelligence ; Quantitative Biology - Quantitative Methods
Thema/Rubrik (Code)	541 ; 006
Erscheinungsdatum	2021-01-28
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Buch ; Online: Neural Empirical Bayes

Saremi, Saeed / Hyvarinen, Aapo

2019

Abstract: We formulate a novel framework that unifies kernel density estimation and empirical Bayes, where we address a broad set of problems in unsupervised learning with a geometric interpretation rooted in the concentration of measure phenomenon. We start by ... ...

Abstract	We formulate a novel framework that unifies kernel density estimation and empirical Bayes, where we address a broad set of problems in unsupervised learning with a geometric interpretation rooted in the concentration of measure phenomenon. We start by energy estimation based on a denoising objective which recovers the original/clean data X from its measured/noisy version Y with empirical Bayes least squares estimator. The setup is rooted in kernel density estimation, but the log-pdf in Y is parametrized with a neural network, and crucially, the learning objective is derived for any level of noise/kernel bandwidth. Learning is efficient with double backpropagation and stochastic gradient descent. An elegant physical picture emerges of an interacting system of high-dimensional spheres around each data point, together with a globally-defined probability flow field. The picture is powerful: it leads to a novel sampling algorithm, a new notion of associative memory, and it is instrumental in designing experiments. We start with extreme denoising experiments. Walk-jump sampling is defined by Langevin MCMC walks in Y, along with asynchronous empirical Bayes jumps to X. Robbins associative memory is defined by a deterministic flow to attractors of the learned probability flow field. Finally, we observed the emergence of remarkably rich creative modes in the regime of highly overlapping spheres. Comment: 23 pages, 9 figures
Schlagwörter	Statistics - Machine Learning ; Computer Science - Machine Learning
Thema/Rubrik (Code)	005
Erscheinungsdatum	2019-03-06
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Zum Seitenanfang

Ihre letzten Suchen

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED

Zusatzmaterialien

Kategorien

Über subito bestellen

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED

Zusatzmaterialien

Kategorien

Über subito bestellen

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED