scholarly journals Optimal forgetting: Semantic compression of episodic memories

2020 ◽  
Author(s):  
David G. Nagy ◽  
Balázs Török ◽  
Gergő Orbán
Keyword(s):  
Information Theory ◽  
Resource Constraints ◽  
Human Memory ◽  
Lossy Compression ◽  
Generative Models ◽  
Generative Model ◽  
Complex Data ◽  
Environmental Statistics ◽  
Wide Range ◽  
Memory Resources

AbstractIt has extensively been documented that human memory exhibits a wide range of systematic distortions, which have been associated with resource constraints. Resource constraints on memory can be formalised in the normative framework of lossy compression, however traditional lossy compression algorithms result in qualitatively different distortions to those found in experiments with humans. We argue that the form of distortions is characteristic of relying on a generative model adapted to the environment for compression. We show that this semantic compression framework can provide a unifying explanation of a wide variety of memory phenomena. We harness recent advances in learning deep generative models, that yield powerful tools to approximate generative models of complex data. We use three datasets, chess games, natural text, and hand-drawn sketches, to demonstrate the effects of semantic compression on memory performance. Our model accounts for memory distortions related to domain expertise, gist-based distortions, contextual effects, and delayed recall.Author summaryHuman memory performs surprisingly poorly in many everyday tasks, which have been richly documented in laboratory experiments. While constraints on memory resources necessarily imply a loss of information, it is possible to do well or badly in relation to available memory resources. In this paper we recruit information theory, which establishes how to optimally lose information based on prior and complete knowledge of environmental statistics. For this, we address two challenges. 1, The environmental statistics is not known for the brain, rather these have to be learned over time from limited observations. 2, Information theory does not specify how different distortions of original experiences should be penalised. In this paper we tackle these challenges by assuming that a latent variable generative model of the environment is maintained in semantic memory. We show that compression of experiences through a generative model gives rise to systematic distortions that qualitatively correspond to a diverse range of observations in the experimental literature.

Implementation of Biologically Inspired Components in Embedded Vision Systems

2012 ◽  
pp. 307-345 ◽  
Author(s):  
Christopher Wing Hong Ngau ◽  
Li-Minn Ang ◽  
Kah Phooi Seng
Keyword(s):  
Field Programmable Gate Array ◽  
Resource Constraints ◽  
Low Complexity ◽  
Primary Concern ◽  
Complex Data ◽  
Biologically Inspired ◽  
Computational Speed ◽  
Visual Tasks ◽  
Field Programmable ◽  
Memory Resources

Studies in the area of computational vision have shown the capability of visual attention (VA) processing in aiding various visual tasks by providing a means for simplifying complex data handling and supporting action decisions using readily available low-level features. Due to the inclusion of computational biological vision components to mimic the mechanism of the human visual system, VA processing is computationally complex with heavy memory requirements and is often found implemented in workstations with unapplied resource constraints. In embedded systems, the computational capacity and memory resources are of a primary concern. To allow VA processing in such systems, the chapter presents a low complexity, low memory VA model based on an established mainstream VA model that addresses critical factors in terms of algorithm complexity, memory requirements, computational speed, and salience prediction performance to ensure the reliability of the VA processing in an environment with limited resources. Lastly, a custom softcore microprocessor-based hardware implementation on a Field-Programmable Gate Array (FPGA) is used to verify the implementation feasibility of the presented low complexity, low memory VA model.

scholarly journals Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian deep learning

2021 ◽  
Vol 118 (16) ◽  
pp. e2020324118
Author(s):  
Biwei Dai ◽  
Uroš Seljak
Keyword(s):  
Dark Matter ◽  
Deep Learning ◽  
Generative Models ◽  
Generative Model ◽  
Effective Theory ◽  
High Dimensions ◽  
Wide Range ◽  
Hydrodynamical Simulations ◽  
Physical Laws ◽  
Very High

The goal of generative models is to learn the intricate relations between the data to create new simulated data, but current approaches fail in very high dimensions. When the true data-generating process is based on physical processes, these impose symmetries and constraints, and the generative model can be created by learning an effective description of the underlying physics, which enables scaling of the generative model to very high dimensions. In this work, we propose Lagrangian deep learning (LDL) for this purpose, applying it to learn outputs of cosmological hydrodynamical simulations. The model uses layers of Lagrangian displacements of particles describing the observables to learn the effective physical laws. The displacements are modeled as the gradient of an effective potential, which explicitly satisfies the translational and rotational invariance. The total number of learned parameters is only of order 10, and they can be viewed as effective theory parameters. We combine N-body solver fast particle mesh (FastPM) with LDL and apply it to a wide range of cosmological outputs, from the dark matter to the stellar maps, gas density, and temperature. The computational cost of LDL is nearly four orders of magnitude lower than that of the full hydrodynamical simulations, yet it outperforms them at the same resolution. We achieve this with only of order 10 layers from the initial conditions to the final output, in contrast to typical cosmological simulations with thousands of time steps. This opens up the possibility of analyzing cosmological observations entirely within this framework, without the need for large dark-matter simulations.

scholarly journals Syllabification of the Divine Comedy

2021 ◽  
Vol 14 (3) ◽  
pp. 1-26
Author(s):  
Andrea Asperti ◽  
Stefano Dal Bianco
Keyword(s):  
Text Processing ◽  
Solution Space ◽  
Generative Models ◽  
Divine Comedy ◽  
Point Of View ◽  
Computer Assisted ◽  
Wide Range ◽  
The Divine Comedy ◽  
Left And Right ◽  
Assisted Analysis

We provide a syllabification algorithm for the Divine Comedy using techniques from probabilistic and constraint programming. We particularly focus on the synalephe , addressed in terms of the "propensity" of a word to take part in a synalephe with adjacent words. We jointly provide an online vocabulary containing, for each word, information about its syllabification, the location of the tonic accent, and the aforementioned synalephe propensity, on the left and right sides. The algorithm is intrinsically nondeterministic, producing different possible syllabifications for each verse, with different likelihoods; metric constraints relative to accents on the 10th, 4th, and 6th syllables are used to further reduce the solution space. The most likely syllabification is hence returned as output. We believe that this work could be a major milestone for a lot of different investigations. From the point of view of digital humanities it opens new perspectives on computer-assisted analysis of digital sources, comprising automated detection of anomalous and problematic cases, metric clustering of verses and their categorization, or more foundational investigations addressing, e.g., the phonetic roles of consonants and vowels. From the point of view of text processing and deep learning, information about syllabification and the location of accents opens a wide range of exciting perspectives, from the possibility of automatic learning syllabification of words and verses to the improvement of generative models, aware of metric issues, and more respectful of the expected musicality.

Equivariant Adversarial Network for Image-to-image Translation

2021 ◽  
Vol 17 (2s) ◽  
pp. 1-14
Author(s):  
Masoumeh Zareapoor ◽  
Jie Yang
Keyword(s):  
State Of The Art ◽  
Generative Models ◽  
Generative Model ◽  
Target Domain ◽  
Adversarial Network ◽  
Proposed Model ◽  
Image Translation ◽  
Great Performance ◽  
Representative Model ◽  
The Ideal

Image-to-Image translation aims to learn an image from a source domain to a target domain. However, there are three main challenges, such as lack of paired datasets, multimodality, and diversity, that are associated with these problems and need to be dealt with. Convolutional neural networks (CNNs), despite of having great performance in many computer vision tasks, they fail to detect the hierarchy of spatial relationships between different parts of an object and thus do not form the ideal representative model we look for. This article presents a new variation of generative models that aims to remedy this problem. We use a trainable transformer, which explicitly allows the spatial manipulation of data within training. This differentiable module can be augmented into the convolutional layers in the generative model, and it allows to freely alter the generated distributions for image-to-image translation. To reap the benefits of proposed module into generative model, our architecture incorporates a new loss function to facilitate an effective end-to-end generative learning for image-to-image translation. The proposed model is evaluated through comprehensive experiments on image synthesizing and image-to-image translation, along with comparisons with several state-of-the-art algorithms.

scholarly journals Retrosynthetic Accessibility Score (RAscore) - Rapid Machine Learned Synthesizability Classification from AI Driven Retrosynthetic Planning

2020 ◽  
Author(s):  
Amol Thakkar ◽  
Veronika Chadimova ◽  
Esben Jannik Bjerrum ◽  
Ola Engkvist ◽  
Jean-Louis Reymond
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Virtual Screening ◽  
Generative Models ◽  
Synthetic Route ◽  
Synthetic Accessibility ◽  
Wide Range ◽  
Computer Aided ◽  
Synthesis Planning ◽  
Retrosynthetic Analysis

<p>Computer aided synthesis planning (CASP) is part of a suite of artificial intelligence (AI) based tools that are able to propose synthesis to a wide range of compounds. However, at present they are too slow to be used to screen the synthetic feasibility of millions of generated or enumerated compounds before identification of potential bioactivity by virtual screening (VS) workflows. Herein we report a machine learning (ML) based method capable of classifying whether a synthetic route can be identified for a particular compound or not by the CASP tool AiZynthFinder. The resulting ML models return a retrosynthetic accessibility score (RAscore) of any molecule of interest, and computes 4,500 times faster than retrosynthetic analysis performed by the underlying CASP tool. The RAscore should be useful for the pre-screening millions of virtual molecules from enumerated databases or generative models for synthetic accessibility and produce higher quality databases for virtual screening of biological activity. </p>

scholarly journals SMILES-Based Deep Generative Scaffold Decorator for De-Novo Drug Design

2020 ◽  
Author(s):  
Josep Arús-Pous ◽  
Atanas Patronov ◽  
Esben Jannik Bjerrum ◽  
Christian Tyrchan ◽  
Jean-Louis Reymond ◽  
...  
Keyword(s):  
Data Augmentation ◽  
De Novo ◽  
Chemical Space ◽  
Generative Models ◽  
Synthetic Chemistry ◽  
Specific Knowledge ◽  
De Novo Drug Design ◽  
Wide Range ◽  
Small Set ◽  
Synthetic Approaches

Molecular generative models trained with small sets of molecules represented as SMILES strings are able to generate large regions of the chemical space. Unfortunately, due to the sequential nature of SMILES strings, these models are not able to generate molecules given a scaffold (i.e. partially-built molecules with explicit attachment points). Herein we report a new SMILES-based molecular generative architecture that generates molecules from scaffolds and can be trained from any arbitrary molecular set. This is possible thanks to a new molecular set pre-processing algorithm that exhaustively cuts all combinations of acyclic bonds of every molecule, obtaining a large number of scaffold-decorations combinations. Moreover, it serves as a data augmentation technique and can be readily coupled with randomized SMILES to obtain even better results with small sets. Two examples showcasing the potential of the architecture in medicinal and synthetic chemistry are described: First, models were trained with a training set obtained from a small set of Dopamine Receptor D2 (DRD2) active modulators and were able to meaningfully decorate a wide range of scaffolds and obtain molecular series predicted active on DRD2. Second, a larger set of drug-like molecules from ChEMBL was selectively sliced using synthetic chemistry constraints (RECAP rules). Moreover, the resulting scaffold-decorations were filtered to only allow decorations that were fragment-like. This allowed models trained with this dataset to selectively decorate diverse scaffolds with fragments that were generally predicted to be synthesizable and attachable to the scaffold using known synthetic approaches. In both cases, the models were already able to decorate molecules using specific knowledge without the need to add it with other techniques, such as reinforcement learning. We envision that this architecture will become a useful addition to the already existent architectures for de-novo molecular generation.

scholarly journals Conditional Wasserstein Generative Adversarial Networks for Fast Detector Simulation

2021 ◽  
Vol 251 ◽  
pp. 03055
Author(s):  
John Blue ◽  
Braden Kronheim ◽  
Michelle Kuchera ◽  
Raghuram Ramanujan
Keyword(s):  
High Energy Physics ◽  
High Energy ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Detector Response ◽  
Event Simulation ◽  
Simulation Process ◽  
Adversarial Networks ◽  
Wide Range ◽  
Detector Simulation

Detector simulation in high energy physics experiments is a key yet computationally expensive step in the event simulation process. There has been much recent interest in using deep generative models as a faster alternative to the full Monte Carlo simulation process in situations in which the utmost accuracy is not necessary. In this work we investigate the use of conditional Wasserstein Generative Adversarial Networks to simulate both hadronization and the detector response to jets. Our model takes the 4-momenta of jets formed from partons post-showering and pre-hadronization as inputs and predicts the 4-momenta of the corresponding reconstructed jet. Our model is trained on fully simulated tt events using the publicly available GEANT-based simulation of the CMS Collaboration. We demonstrate that the model produces accurate conditional reconstructed jet transverse momentum (pT) distributions over a wide range of pT for the input parton jet. Our model takes only a fraction of the time necessary for conventional detector simulation methods, running on a CPU in less than a millisecond per event.

scholarly journals A Systematic Survey on Deep Generative Models for Graph Generation

2020 ◽  
Author(s):  
Xiaojie Guo ◽  
Liang Zhao
Keyword(s):  
Generative Models ◽  
Future Research ◽  
Specific Domain ◽  
Research Directions ◽  
Wide Range ◽  
Data Representations ◽  
Future Research Directions ◽  
Definition Of ◽  
Rich History ◽  
Graph Generation

Graphs are important data representations for describing objects and their relationships, which appear in a wide diversity of real-world scenarios. As one of a critical problem in this area, graph generation considers learning the distributions of given graphs and generating more novel graphs. Owing to its wide range of applications, generative models for graphs have a rich history, which, however, are traditionally hand-crafted and only capable of modeling a few statistical properties of graphs. Recent advances in deep generative models for graph generation is an important step towards improving the fidelity of generated graphs and paves the way for new kinds of applications. This article provides an extensive overview of the literature in the field of deep generative models for graph generation. Firstly, the formal definition of deep generative models for the graph generation as well as preliminary knowledge is provided. Secondly, two taxonomies of deep generative models for unconditional, and conditional graph generation respectively are proposed; the existing works of each are compared and analyzed. After that, an overview of the evaluation metrics in this specific domain is provided. Finally, the applications that deep graph generation enables are summarized and five promising future research directions are highlighted.

scholarly journals Monte Carlo and Reconstruction Membership Inference Attacks against Generative Models

2019 ◽  
Vol 2019 (4) ◽  
pp. 232-249 ◽  
Author(s):  
Benjamin Hilprecht ◽  
Martin Härterich ◽  
Daniel Bernau
Keyword(s):  
Data Privacy ◽  
Information Leakage ◽  
Generative Models ◽  
Generative Model ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Data Sets ◽  
Success Rates ◽  
Model Quality ◽  
Type Formalization

Abstract We present two information leakage attacks that outperform previous work on membership inference against generative models. The first attack allows membership inference without assumptions on the type of the generative model. Contrary to previous evaluation metrics for generative models, like Kernel Density Estimation, it only considers samples of the model which are close to training data records. The second attack specifically targets Variational Autoencoders, achieving high membership inference accuracy. Furthermore, previous work mostly considers membership inference adversaries who perform single record membership inference. We argue for considering regulatory actors who perform set membership inference to identify the use of specific datasets for training. The attacks are evaluated on two generative model architectures, Generative Adversarial Networks (GANs) and Variational Autoen-coders (VAEs), trained on standard image datasets. Our results show that the two attacks yield success rates superior to previous work on most data sets while at the same time having only very mild assumptions. We envision the two attacks in combination with the membership inference attack type formalization as especially useful. For example, to enforce data privacy standards and automatically assessing model quality in machine learning as a service setups. In practice, our work motivates the use of GANs since they prove less vulnerable against information leakage attacks while producing detailed samples.

scholarly journals Towards Consistent Variational Auto-Encoding (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13869-13870
Author(s):  
Yijing Liu ◽  
Shuyu Lin ◽  
Ronald Clark
Keyword(s):  
Original Data ◽  
Generative Models ◽  
Generative Model ◽  
Approximate Inference ◽  
Inference Model ◽  
Approach To Learning ◽  
Successful Approach ◽  
Data Point ◽  
Reconstructed Data

Variational autoencoders (VAEs) have been a successful approach to learning meaningful representations of data in an unsupervised manner. However, suboptimal representations are often learned because the approximate inference model fails to match the true posterior of the generative model, i.e. an inconsistency exists between the learnt inference and generative models. In this paper, we introduce a novel consistency loss that directly requires the encoding of the reconstructed data point to match the encoding of the original data, leading to better representations. Through experiments on MNIST and Fashion MNIST, we demonstrate the existence of the inconsistency in VAE learning and that our method can effectively reduce such inconsistency.

Sign in / Sign up

Export Citation Format

Share Document