26 papers · ranked by Valyu relevance
Alexander Ororbia, Daniel Kifer
Neural generative models can be used to learn complex probability distributions from data, to sample from them, and to produce probability density estimates. We propose a computational framework for developing neural generative models inspired by the theory of predictive processing in the brain. According to predictive…
Ambuj Tewari
Beginning with text and images, generative AI has expanded to audio, video, computer code, and molecules. Yet, if generative AI is the answer, what is the question? We explore the foundations of generation as a distinct machine learning task with connections to prediction, compression, and decision-making. We survey…
Giorgio Franceschelli, Mirco Musolesi
Generative Artificial Intelligence (AI) is one of the most exciting developments in Computer Science of the last decade. At the same time, Reinforcement Learning (RL) has emerged as a very successful paradigm for a variety of machine learning tasks. In this survey, we discuss the state of the art, opportunities and…
Ran He, Jie Cao, Tieniu Tan
Generative artificial intelligence (GAI) has recently achieved significant success, enabling anyone to create texts, images, videos and even computer codes while providing insights that might not be possible with traditional tools. To stimulate future research, this work provides a brief summary of the ongoing and…
Authors not listed
In recent years, generative deep learning has emerged as a transformative approach in drug design, promising to explore the vast chemical space and generate novel molecules with desired biological properties. This perspective examines the challenges and opportunities of applying generative models to drug discovery…
Sandeep Singh Sengar, Affan Bin Hasan, Sanjay Kumar, Fiona Carroll
In recent years, the study of artificial intelligence (AI) has undergone a paradigm shift. This has been propelled by the groundbreaking capabilities of generative models both in supervised and unsupervised learning scenarios. Generative AI has shown state-of-the-art performance in solving perplexing real-world…
Ardavan Bidgoli, Pedro Veloso
Generative systems have a signifcant potential to synthesize innovative design alternatives. Still, most of the common systems that have been adopted in design require the designer to explicitly defne the specifcations of the procedures and, in some cases, the design space. In contrast, a generative system could…
Romain Lopez, Adam Gayoso, Nir Yosef
Generative models provide a well-established statistical framework for evaluating uncertainty and deriving conclusions from large data sets especially in the presence of noise, sparsity, and bias. Initially developed for computer vision and natural language processing, these models have been shown to effectively…
Tom M George, Caswell Barry, Kimberly Stachenfeld, Claudia Clopath + 1 more
Advances in generative models have recently revolutionised machine learning. Meanwhile, in neuroscience, generative models have long been thought fundamental to animal intelligence. Understanding the biological mechanisms that support these processes promises to shed light on the relationship between biological and…
Jens Nußberger, Frederic Boesel, Stefan Lenz, Harald Binder + 1 more
Deep generative models can be trained to represent the joint distribution of data, such as measurements of single nucleotide polymorphisms (SNPs) from several individuals. Subsequently, synthetic observations are obtained by drawing from this distribution. This has been shown to be useful for several tasks, such as…
Authors not listed
Solving optimization problems, especially for nonlinear and constrained systems, is a challenge. Decades of specialized algorithms have been developed for general and special cases of root finding, minimization (including constraints), for parameter estimation, and mapping connected spaces. These approaches typically…
Sobhan Babu, Ravindra Guravannavar
GANs have two competing modules: the generator module is trained to generate new examples, and the discriminator module is trained to discriminate real examples from generated examples. The training procedure of GAN is modeled as a finitely repeated simultaneous game. Each module tries to increase its performance at…
Ivilin Stoianov, Domenico Maisto, Giovanni Pezzulo
We advance a novel computational theory of the hippocampal formation as a hierarchical generative model that organizes sequential experiences, such as rodent trajectories during spatial navigation, into coherent spatiotemporal contexts. We propose that the hippocampal generative model is endowed with inductive biases…
Kevin Korfmann, Oscar E Gaggiotti, Matteo Fumagalli, Andrea Betancourt
'Andrea Betancourt'] Title: Abstract Population genetics is transitioning into a data-driven discipline thanks to the availability of large-scale genomic data and the need to study increasingly complex evolutionary scenarios. With likelihood and Bayesian approaches becoming either intractable or computationally…
Sihan Xie, Thierry Tribout, Didier Boichard, Blaise Hanczar + 2 more
Deep generative models open new avenues for simulating realistic genomic data while preserving privacy and addressing data accessibility constraints. While previous studies have primarily focused on generating gene expression or haplotype data, this study explores generating genotype data in both unconditioned and…
Authors not listed
The integration of machine learning methods is transforming many areas of research by, for instance, accelerating molecular dynamics simulations and enabling improved prediction and optimization of chemical reactions. However, despite this progress, the adoption of data-driven approaches in atomic layer deposition…
Laura Desirèe Di Paolo, Ben White, Avel Guénin-Carlut, Axel Constant + 1 more
'Andy Clark'] Human learning essentially involves embodied interactions with the material world. But our worlds now include increasing numbers of powerful and (apparently) disembodied generative artificial intelligence (AI). In what follows we ask how best to understand these new (somewhat ‘alien’, because of their…
Authors not listed
Machine learning is increasingly used to predict reaction properties such as barrier heights, reaction energies, rates, or yields, as well as the underlying molecular geometries, including transition state structures. While such predictions have the potential to provide mechanistic insight for high-impact applications…
Philipp Renz, Dries Van Rompaey, Jörg Kurt Wegner, Sepp Hochreiter + 1 more
There has been a wave of generative models for molecules triggered by advances in the field of Deep Learning. These generative models are often used to optimize chemical compounds towards particular properties or a desired biological activity. The evaluation of generative models remains challenging and suggested…
Authors not listed
The vastness of chemical space presents a long-standing challenge for the exploration of new compounds with pre-determined properties. In materials science, crystal structure prediction has become a mature tool for mapping from composition to structure based on global optimisation techniques. Generative artificial…
Danilo Jimenez Rezende, Shakir Mohamed, Ivo Danihelka, Karol Gregor + 1 more
'Daan Wierstra'] Humans have an impressive ability to reason about new concepts and experiences from just a single example. In particular, humans have an ability for one-shot generalization: an ability to encounter a new concept, understand its structure, and then be able to generate compelling alternative variations…
Ghislain St-Yves, Thomas Naselaris
We consider the inference problem of reconstructing a visual stimulus from brain activity measurements (e.g. fMRI) that encode this stimulus. Recovering a complete image is complicated by the fact that neural representations are noisy, high-dimensional, and contain incomplete information about image details. Thus…
Alex Hawkins-Hooker, Florence Depardieu, Sebastien Baur, Guillaume Couairon + 2 more
The design of novel proteins with specified function and controllable biochemical properties is a longstanding goal in bio-engineering with potential applications across medicine and nanotechnology. The vast expansion of protein sequence databases over the last decades provides an opportunity for new approaches which…
Rebekah L. Waikel, Amna A. Othman, Tanviben Patel, Suzanna Ledgister Hanchard + 4 more
Deep learning (DL), a subfield of artificial intelligence (AI), has become a powerful tool in biomedical research, with strong clinical potential.1,2,3 Generative AI is a relatively new branch of DL in which new data can be created through training on existing data sets. One type of generative AI that can be used for…
Michael Alverson, Sterling Baird, Ryan Murdock, Taylor Sparks
The idea of materials discovery has excited and perplexed research scientists for centuries. Several different methods have been employed to find new types of materials, ranging from the arbitrary replacement of atoms in a crystal structure to advanced machine learning methods for predicting entirely new crystal…
Movitz Lenninger, Whan-Hyuk Choi, Hansol Choi
Predictive processing models suggest that the brain decides actions through inference. While most predictive models have been formalized using explicit representations of the probability distributions, using explicit structures and parameters, we explore an alternative representation using an implicit model known as…