SCHU-20: E-Cadherin Predictive Value for Recurrence of Bladder Noninvasive Tumors (Ta-T1)

Bengió, Verónica; Arribillaga, Leandro; Hay, Matthew; Orellana, S.D.B.; Bengió, Rubén H.

doi:10.1016/j.urology.2008.08.028

Cited by 12 publications

(33 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, by also drawing upon biological details in designing AI-architectures, we may find ourselves with access to invaluable inductive biases which might be otherwise overlooked. Two examples that come to mind include recent proposals by Bengio and LeCun with respect to "GFlowNets" and "Joint Embedding Predictive Architectures" (Bengio et al, 2022;LeCun, 2022). We believe these efforts in creating autonomous and generally intelligent systems may benefit by incorporating principles of G-SLAM, such as the creation of systems capable of handling loop trajectories as potentially enabling greater open-ended and life-long learning, or in looking towards hybrid systems similar to LatentSLAM as potentially allowing for explicit representations and symbolic processing.…”

Section: G(eneralized-)slam As Core Cognitive Processmentioning

confidence: 99%

Generalized Simultaneous Localization and Mapping (G-SLAM) as unification framework for natural and artificial intelligences: towards reverse engineering the hippocampal/entorhinal system and principles of high-level cognition

Safron

Çatal²,

Verbelen³

2022

Front. Syst. Neurosci.

View full text Add to dashboard Cite

Simultaneous localization and mapping (SLAM) represents a fundamental problem for autonomous embodied systems, for which the hippocampal/entorhinal system (H/E-S) has been optimized over the course of evolution. We have developed a biologically-inspired SLAM architecture based on latent variable generative modeling within the Free Energy Principle and Active Inference (FEP-AI) framework, which affords flexible navigation and planning in mobile robots. We have primarily focused on attempting to reverse engineer H/E-S “design” properties, but here we consider ways in which SLAM principles from robotics may help us better understand nervous systems and emergent minds. After reviewing LatentSLAM and notable features of this control architecture, we consider how the H/E-S may realize these functional properties not only for physical navigation, but also with respect to high-level cognition understood as generalized simultaneous localization and mapping (G-SLAM). We focus on loop-closure, graph-relaxation, and node duplication as particularly impactful architectural features, suggesting these computational phenomena may contribute to understanding cognitive insight (as proto-causal-inference), accommodation (as integration into existing schemas), and assimilation (as category formation). All these operations can similarly be describable in terms of structure/category learning on multiple levels of abstraction. However, here we adopt an ecological rationality perspective, framing H/E-S functions as orchestrating SLAM processes within both concrete and abstract hypothesis spaces. In this navigation/search process, adaptive cognitive equilibration between assimilation and accommodation involves balancing tradeoffs between exploration and exploitation; this dynamic equilibrium may be near optimally realized in FEP-AI, wherein control systems governed by expected free energy objective functions naturally balance model simplicity and accuracy. With respect to structure learning, such a balance would involve constructing models and categories that are neither too inclusive nor exclusive. We propose these (generalized) SLAM phenomena may represent some of the most impactful sources of variation in cognition both within and between individuals, suggesting that modulators of H/E-S functioning may potentially illuminate their adaptive significances as fundamental cybernetic control parameters. Finally, we discuss how understanding H/E-S contributions to G-SLAM may provide a unifying framework for high-level cognition and its potential realization in artificial intelligences.

show abstract

Section: G(eneralized-)slam As Core Cognitive Processmentioning

confidence: 99%

Generalized Simultaneous Localization and Mapping (G-SLAM) as unification framework for natural and artificial intelligences: towards reverse engineering the hippocampal/entorhinal system and principles of high-level cognition

Safron

Çatal²,

Verbelen³

2022

Front. Syst. Neurosci.

View full text Add to dashboard Cite

show abstract

“…In this section, we present our proposed active learning algorithm based on GFlowNets (Bengio et al, 2021a). We only present the relevant key results, and refer the reader to Bengio et al (2021b) for a thorough mathematical treatment of GFlowNets. Figure 2 provides an overview of our proposed approach and Algorithm 2 describes the details of the algorithm.…”

Section: Gflownets For Sequence Designmentioning

confidence: 99%

“…In the context of active learning, this uncertainty can be a strong signal to guide exploration in novel parts of the space and has been traditionally used in Bayesian optimization (Angermueller et al, 2019;Swersky et al, 2020;Jain et al, 2021). Bengio et al (2021b) hypothesize that using information about the uncertainty of the reward function can also lead to more efficient exploration in GFlowNets. We study this hypothesis, by incorporating the model uncertainty of the reward function for training GFlowNets.…”

Section: Incorporating Epistemic Uncertaintymentioning

confidence: 99%

Biological Sequence Design with GFlowNets

Moksh¹,

Bengio²,

Garcia³

et al. 2022

Preprint

View full text Add to dashboard Cite

Design of de novo biological sequences with desired properties, like protein and DNA sequences, often involves an active loop with several rounds of molecule ideation and expensive wet-lab evaluations. These experiments can consist of multiple stages, with increasing levels of precision and cost of evaluation, where candidates are filtered. This makes the diversity of proposed candidates a key consideration in the ideation phase. In this work, we propose an active learning algorithm leveraging epistemic uncertainty estimation and the recently proposed GFlowNets as a generator of diverse candidate solutions, with the objective to obtain a diverse batch of useful (as defined by some utility function, for example, the predicted anti-microbial activity of a peptide) and informative candidates after each round. We also propose a scheme to incorporate existing labeled datasets of candidates, in addition to a reward function, to speed up learning in GFlowNets. We present empirical results on several biological sequence design tasks, and we find that our method generates more diverse and novel batches with high scoring candidates compared to existing approaches.

show abstract

“…Alternative objectives proposed by Bengio et al (2021b); Malkin et al (2022) require a model to produce 3 outputs: the scalar log Z θ , a forward policy P F (•|•; θ), and a backward policy that produces distributions P B (•|s; θ) over the parents of an input state s. (When action sequences are sampled in reverse from P B , we will use dashed arrows s s to indicate that the action s→s has been sampled against the direction of the DAG edges. The θ will be dropped from P F and P B notation when it does not cause ambiguity.…”

Section: Gflownetsmentioning

confidence: 99%

“…Canonical design of P B . Bengio et al (2021b) noted that while there may be multiple Markovian flows satisfying (2), for any choice of a fixed backward policy P B , there is a unique forward policy P F such that the corresponding P T (x) is proportional to the reward. Malkin et al (2022) suggested fixing P B (•|s) to be uniform over the parents of every state s as a canonical choice.…”

Section: Gflownet Training Towards a Target Distributionmentioning

confidence: 99%

Generative Flow Networks for Discrete Probabilistic Modeling

Zhang¹,

Malkin²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present energy-based generative flow networks (EB-GFN), a novel probabilistic modeling algorithm for high-dimensional discrete data. Building upon the theory of generative flow networks (GFlowNets; Bengio et al., 2021b), we model the generation process by a stochastic data construction policy and thus amortize expensive MCMC exploration into a fixed number of actions sampled from a GFlowNet. We show how GFlowNets can approximately perform large-block Gibbs sampling to mix between modes. We propose a framework to jointly train a GFlowNet with an energy function, so that the GFlowNet learns to sample from the energy distribution, while the energy learns with an approximate MLE objective with negative samples from the GFlowNet. We demonstrate EB-GFN's effectiveness on various probabilistic modeling tasks.

show abstract

SCHU-20: E-Cadherin Predictive Value for Recurrence of Bladder Noninvasive Tumors (Ta-T1)

Cited by 12 publications

References 0 publications

Generalized Simultaneous Localization and Mapping (G-SLAM) as unification framework for natural and artificial intelligences: towards reverse engineering the hippocampal/entorhinal system and principles of high-level cognition

Generalized Simultaneous Localization and Mapping (G-SLAM) as unification framework for natural and artificial intelligences: towards reverse engineering the hippocampal/entorhinal system and principles of high-level cognition

Biological Sequence Design with GFlowNets

Generative Flow Networks for Discrete Probabilistic Modeling

Contact Info

Product

Resources

About