Manuela Veloso's research while affiliated with Jpmorgan Chase & Co. and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (725)
Organizations around the world schedule jobs (programs) regularly to perform various tasks dictated by their end users. With the major movement toward using a cloud computing infrastructure, our organization follows a hybrid approach with both cloud and on-prem servers. The objective of this work is to perform capacity planning, i.e., estimate reso...
A myriad of different Large Language Models (LLMs) face a common challenge in contextually analyzing table question-answering tasks. These challenges are engendered from (1) finite context windows for large tables, (2) multi-faceted discrepancies amongst tokenization patterns against cell boundaries, and (3) various limitations stemming from data c...
This paper proposes Progressive Inference - a framework to compute input attributions to explain the predictions of decoder-only sequence classification models. Our work is based on the insight that the classification head of a decoder-only Transformer model can be used to make intermediate predictions by evaluating them at different points in the...
We introduce T-CREx, a novel model-agnostic method for local and global counterfactual explanation (CE), which summarises recourse options for both individuals and groups in the form of human-readable rules. It leverages tree-based surrogate models to learn the counterfactual rules, alongside 'metarules' denoting their regions of optimality, provid...
Discrete optimization belongs to the set of N P-hard problems, spanning fields such as mixed-integer programming and combinatorial optimization. A current standard approach to solving convex discrete optimization problems is the use of cutting-plane algorithms, which reach optimal solutions by iteratively adding inequalities known as cuts to refine...
Recent years have seen a surge of machine learning approaches aimed at reducing disparities in model outputs across different subgroups. In many settings, training data may be used in multiple downstream applications by different users, which means it may be most effective to intervene on the training data itself. In this work, we present FairWASP,...
In some applications, planning-monitoring systems generate plans and monitor their execution by other agents. During execution, agents might deviate from these plans for various reasons. The deviation from the expected behavior will be observed by the planning-monitoring system, which will replan in order to provide the agent a new suggested plan....
We study a game between liquidity provider (LP) and liquidity taker agents interacting in an over‐the‐counter market, for which the typical example is foreign exchange. We show how a suitable design of parameterized families of reward functions coupled with shared policy learning constitutes an efficient solution to this problem. By playing against...
Explainable reinforcement learning (XRL) is an emerging subfield of explainable machine learning that has attracted considerable attention in recent years. The goal of XRL is to elucidate the decision-making process of reinforcement learning (RL) agents in sequential decision-making settings. Equipped with this information, practitioners can better...
Large language models such as Open AI's Generative Pre-trained Transformer (GPT) models are proficient at answering questions, but their knowledge is confined to the information present in their training data. This limitation renders them ineffective when confronted with questions about recent developments or non-public documents. Our research prop...
Human demonstration videos are a widely available data source for robot learning and an intuitive user interface for expressing desired behavior. However, directly extracting reusable robot manipulation skills from unstructured human videos is challenging due to the big embodiment difference and unobserved action parameters. To bridge this embodime...
Stochastic optimization (SO) attempts to offer optimal decisions in the presence of uncertainty. Often, the classical formulation of these problems becomes intractable due to (a) the number of scenarios required to capture the uncertainty and (b) the discrete nature of real-world planning problems. To overcome these tractability issues, practitione...
Defining financial goals and formulating actionable plans to achieve them are essential components for ensuring financial health. This task is computationally challenging, given the abundance of factors that can influence one’s financial situation. In this paper, we present the Personal Finance Planner (PFP), which can generate personalized financi...
Creation of a synthetic dataset that faithfully represents the data distribution and simultaneously preserves privacy is a major research challenge. Many space partitioning based approaches have emerged in recent years for answering statistical queries in a differentially private manner. However, for synthetic data generation problem, recent resear...
Time series forecasting is important across various domains for decision-making. In particular, financial time series such as stock prices can be hard to predict as it is difficult to model short-term and long-term temporal dependencies between data points. Convolutional Neural Networks (CNN) are good at capturing local patterns for modeling short-...
Hawkes processes have recently risen to the forefront of tools when it comes to modeling and generating sequential events data. Multidimensional Hawkes processes model both the self and cross-excitation between different types of events and have been applied successfully in various domain such as finance, epidemiology and personalized recommendatio...
Call centers, in which human operators attend clients using textual chat, are very common in modern e-commerce. Training enough skilled operators who are able to provide good service is a challenge. We propose a methodology for the development of an assisting agent that provides online advice to operators while they attend clients. The agent is eas...
The Concept Bottleneck Models (CBMs) of Koh et al. [2020] provide a means to ensure that a neural network based classifier bases its predictions solely on human understandable concepts. The concept labels, or rationales as we refer to them, are learned by the concept labeling component of the CBM. Another component learns to predict the target clas...
Concept bottleneck models perform classification by first predicting which of a list of human provided concepts are true about a datapoint. Then a downstream model uses these predicted concept labels to predict the target label. The predicted concepts act as a rationale for the target prediction. Model trust issues emerge in this paradigm when soft...
We study a game between liquidity provider and liquidity taker agents interacting in an over-the-counter market, for which the typical example is foreign exchange. We show how a suitable design of parameterized families of reward functions coupled with associated shared policy learning constitutes an efficient solution to this problem. Precisely, w...
We introduce ASPiRe (Adaptive Skill Prior for RL), a new approach that leverages prior experience to accelerate reinforcement learning. Unlike existing methods that learn a single skill prior from a large and diverse dataset, our framework learns a library of different distinction skill priors (i.e., behavior priors) from a collection of specialize...
Online learning of Hawkes processes has received increasing attention in the last couple of years especially for modeling a network of actors. However, these works typically either model the rich interaction between the events or the latent cluster of the actors or the network structure between the actors. We propose to model the latent structure o...
Analyzing the layout of a document to identify headers, sections, tables, figures etc. is critical to understanding its content. Deep learning based approaches for detecting the layout structure of document images have been promising. However, these methods require a large number of annotated examples during training, which are both expensive and t...
Hawkes processes have recently gained increasing attention from the machine learning community for their versatility in modeling event sequence data. While they have a rich history going back decades, some of their properties, such as sample complexity for learning the parameters and releasing differentially private versions, are yet to be thorough...
Social robots have been shown to be promising tools for delivering therapeutic tasks for children with Autism Spectrum Disorder (ASD). However, their efficacy is currently limited by a lack of flexibility of the robot’s social behavior to successfully meet therapeutic and interaction goals. Robot-assisted interventions are often based on structured...
Explainable reinforcement learning (XRL) is an emerging subfield of explainable machine learning that has attracted considerable attention in recent years. The goal of XRL is to elucidate the decision-making process of learning agents in sequential decision-making settings. In this survey, we propose a novel taxonomy for organizing the XRL literatu...
Graph neural networks have gained prominence due to their excellent performance in many classification and prediction tasks. In particular, they are used for node classification and link prediction which have a wide range of applications in social networks, biomedical data sets, and financial transaction graphs. Most of the existing work focuses pr...
Retrieving relevant documents from a corpus is typically based on the semantic similarity between the document content and query text. The inclusion of structural relationship between documents can benefit the retrieval mechanism by addressing semantic gaps. However, incorporating these relationships requires tractable mechanisms that balance struc...
![Figure 4: SimNet simulation results for the aneurysm problem [19]....](profile/Olexandr-Isayev/publication/356819410/figure/fig3/AS:1098658720301059@1638952059653/SimNet-simulation-results-for-the-aneurysm-problem-19-Left-patient-specific-geometry_Q320.jpg)
![Figure 7: Graph-Informed Neural Networks (GINNs) [42] provide a...](profile/Olexandr-Isayev/publication/356819410/figure/fig5/AS:1098658720284675@1638952059698/Graph-Informed-Neural-Networks-GINNs-42-provide-a-computational-advantage-while_Q320.jpg)
The original "Seven Motifs" set forth a roadmap of essential methods for the field of scientific computing, where a motif is an algorithmic method that captures a pattern of computation and data movement. We present the "Nine Motifs of Simulation Intelligence", a roadmap for the development and integration of the essential algorithms necessary for...
![Figure 4: SimNet simulation results for the aneurysm problem [19]....](profile/Olexandr-Isayev/publication/362153462/figure/fig3/AS:1180154462244864@1658382158250/SimNet-simulation-results-for-the-aneurysm-problem-19-Left-patient-specific-geometry_Q320.jpg)
![Figure 7: Graph-Informed Neural Networks (GINNs) [42] provide a...](profile/Olexandr-Isayev/publication/362153462/figure/fig5/AS:1180154462244865@1658382158494/Graph-Informed-Neural-Networks-GINNs-42-provide-a-computational-advantage-while_Q320.jpg)
The original "Seven Motifs" set forth a roadmap of essential methods for the field of scientific computing, where a motif is an algorithmic method that captures a pattern of computation and data movement. We present the "Nine Motifs of Simulation Intelligence", a roadmap for the development and integration of the essential algorithms necessary for...
Analyzing the layout of a document to identify headers, sections, tables, figures etc. is critical to understanding its content. Deep learning based approaches for detecting the layout structure of document images have been promising. However, these methods require a large number of annotated examples during training, which are both expensive and t...
Matching companies and investors is usually considered a highly specialized decision making process. Building an AI agent that can automate such recommendation process can significantly help reduce costs, and eliminate human biases and errors. However, limited sample size of financial data-sets and the need for not only good recommendations, but al...
Model-free Reinforcement Learning (RL) requires the ability to sample trajectories by taking actions in the original problem environment or a simulated version of it. Breakthroughs in the field of RL have been largely facilitated by the development of dedicated open source simulators with easy to use frameworks such as OpenAI Gym and its Atari envi...
The success of machine learning models is highly reliant on the quality and robustness of representations. The lack of attention on the robustness of representations may boost risks when using data-driven machine learning models for trading in the financial markets. In this paper, we focus on representations of the limit order book (LOB) data and d...
The success of machine learning models in the financial domain is highly reliant on the quality of the data representation. In this paper, we focus on the representation of limit order book data and discuss the opportunities and challenges for learning representations of such data. We also experimentally analyse the issues associated with existing...
Institutions are increasingly relying on machine learning models to identify and alert on abnormal events, such as fraud, cyber attacks and system failures. These alerts often need to be manually investigated by specialists. Given the operational cost of manual inspections, the suspicious events are selected by alerting systems with carefully desig...
Continuous double auctions such as the limit order book employed by exchanges are widely used in practice to match buyers and sellers of a variety of financial instruments. In this work, we develop an agent-based model for trading in a limit order book and show (1) how opponent modelling techniques can be applied to classify trading agent archetype...
Artificial intelligence (AI) is a science and engineering discipline that is highly relevant to financial services, given the significant amount and diversity of data generated (and consumed) as those services are delivered worldwide. Global banks process billions of international payments each day, while equity exchanges handle trillions of orders...
Active participation of customers in the management of demand, and renewable energy supply, is a critical goal of the Smart Grid vision. However, this is a com-plex problem with numerous scenarios that are difficult to test in field projects. Rich and scalable simulations are required to develop effective strategies and poli-cies that elicit desira...
In this work, we address the problem of symmetry transfer in human-robot collaborative tasks, i.e., how certain actions can be extended to their symmetrical by exploiting symmetries in their execution. We contribute an approach capable of considering the symmetry inherent to a given task, such as the human or robot’s lateral symmetry, abstracting t...
The efficiency of heuristic search depends dramatically on the quality of the heuristic function. For an optimal heuristic search, heuristics that estimate cost-to-goal better typically lead to faster searches. For a sub-optimal heuristic search such as weighted A*, the search speed depends more on the correlation between the heuristic and the true...
Rapidly-exploring random trees (RRTs) are data structures and search algorithms designed to be used in continuous path planning problems. They are one of the most successful state-of-the-art techniques as they offer a great degree of flexibility and reliability. However, their use in other search domains has not been thoroughly analyzed. In this wo...
In this work, we address time-series forecasting as a computer vision task. We capture input data as an image and train a model to produce the subsequent image. This approach results in predicting distributions as opposed to pointwise values. To assess the robustness and quality of our approach, we examine various datasets and multiple evaluation m...
We focus on long-sighted planning for a class of problems with multiple independent tasks that are partially observable and evolve over time. An example problem that falls into this class is a robot waiting multiple tables, referred to as tasks, in a restaurant where customers' satisfaction is partially observable and evolves over time. Our recent...
This paper analyzes, from theoretical and algorithmic perspectives, a class of problems recently introduced in the literature of Markov decision processes—configurable Markov decision processes. In this new class of problems we jointly optimize the probability transition function and associated optimal policy, in order to improve the performance of...
Weighted A* search (wA*) is a popular tool for robot motionplanning. Its efficiency however depends on the quality of heuristic function used. In fact, it has been shown that the correlation between the heuristic function and the true costto-goal significantly affects the efficiency of the search, when used with a large weight on the heuristics. Mo...
We present how we formalize the waiting tables task in a restaurant as a robot planning problem. This formalization was used to test our recently developed algorithms that allow for optimal planning for achieving multiple independent tasks that are partially observable and evolve over time [1], [2].
Current work in explainable reinforcement learning generally produces policies in the form of a decision tree over the state space. Such policies can be used for formal safety verification, agent behavior prediction, and manual inspection of important features. However, existing approaches fit a decision tree after training or use a custom learning...
Traditionally, planning provides for execution plans as sequences of actions with preconditions and effects. Execution monitoring identifies failure conditions when the preconditions of an action do not match the state. Interestingly, planning proceeds by consuming a given initial state and abandoning reasoning about any facts not true in that stat...
Call centers, in which human operators attend clients using textual chat, are very common in modern e-commerce. Training enough skilled operators who are able to provide good service is a challenge. We suggest an algorithm and a method to train and implement an assisting agent that provides on-line advice to operators while they attend clients. The...
Fine-tuning a pre-trained neural language model with a task specific output layer is the de facto approach of late when dealing with document classification. This technique is inadequate when labeled examples are unavailable at training time and when the metadata artifacts in a document must be exploited. We address these challenges by generating d...
A key challenge in robotic food manipulation is modeling the material properties of diverse and deformable food items. We propose using a multimodal sensory approach to interact and play with food that facilitates the ability to distinguish these properties across food items. First, we use a robotic arm and an array of sensors, which are synchroniz...
Current work in explainable reinforcement learning generally produces policies in the form of a decision tree over the state space. Such policies can be used for formal safety verification, agent behavior prediction, and manual inspection of important features. However, existing approaches fit a decision tree after training or use a custom learning...
We present the theoretical analysis and proofs of a recently developed algorithm that allows for optimal planning over long and infinite horizons for achieving multiple independent tasks that are partially observable and evolve over time.
Time series forecasting is essential for decision making in many domains. In this work, we address the challenge of predicting prices evolution among multiple potentially interacting financial assets. A solution to this problem has obvious importance for governments, banks, and investors. Statistical methods such as Auto Regressive Integrated Movin...
A key challenge in robotic food manipulation is modeling the material properties of diverse and deformable food items. We propose using a multimodal sensory approach to interact and play with food that facilitates the ability to distinguish these properties across food items. First, we use a robotic arm and an array of sensors, which are synchroniz...
Time series forecasting is essential for agents to make decisions in many domains. Existing models rely on classical statistical methods to predict future values based on previously observed numerical information. Yet, practitioners often rely on visualizations such as charts and plots to reason about their predictions. Inspired by the end-users, w...
Many business applications involve adversarial relationships in which both sides adapt their strategies to optimize their opposing benefits. One of the key characteristics of these applications is the wide range of strategies that an adversary may choose as they adapt their strategy dynamically to sustain benefits and evade authorities. In this pap...
Financial institutions mostly deal with people. Therefore, characterizing different kinds of human behavior can greatly help institutions for improving their relation with customers and with regulatory offices. In many of such interactions, humans have some internal goals, and execute some actions within the financial system that lead them to achie...
Task specific fine-tuning of a pre-trained neural language model using a custom softmax output layer is the de facto approach of late when dealing with document classification problems. This technique is not adequate when labeled examples are not available at training time and when the metadata artifacts in a document must be exploited. We address...
Supervised learning classifiers inevitably make mistakes in production, perhaps mis-labeling an email, or flagging an otherwise routine transaction as fraudulent. It is vital that the end users of such a system are provided with a means of relabeling data points that they deem to have been mislabeled. The classifier can then be retrained on the rel...
We introduce a data management problem called metadata debt, to identify the mapping between data concepts and their logical representations. We describe how this mapping can be learned using semisupervised topic models based on low-rank matrix factorizations that account for missing and noisy labels, coupled with sparsity penalties to improve loca...
Business analysts create billions of slide decks, reports and documents annually. Most of these documents have well-defined structure comprising of similar content generated from data. We present 'AI pptX', a novel AI framework for creating and modifying documents as well as extract insights in the form of natural language sentences from data. AI p...
Training multi-agent systems (MAS) to achieve realistic equilibria gives us a useful tool to understand and model real-world systems. We consider a general sum partially observable Markov game where agents of different types share a single policy network, conditioned on agent-specific information. This paper aims at i) formally understanding equili...
We introduce a novel framework to account for sensitivity to rewards uncertainty in sequential decision-making problems. While risk-sensitive formulations for Markov decision processes studied so far focus on the distribution of the cumulative reward as a whole, we aim at learning policies sensitive to the uncertain/stochastic nature of the rewards...
We focus on domains where a robot is required to accomplish a set of tasks that are partially observable and evolve independently of each other according to their dynamics. An example domain is a restaurant setting where a robot waiter should take care of an ongoing stream of tasks, namely serving a number of tables, including delivering food to th...
To encourage the development of methods with reproducible and robust training behavior, we propose a challenge paradigm where competitors are evaluated directly on the performance of their learning procedures rather than pre-trained agents. Since competition organizers re-train proposed methods in a controlled setting they can guarantee reproducibi...
![Worked example with N=3\documentclass[12pt]{minimal}...](profile/Kim-Baraka/publication/340961211/figure/fig3/AS:960469288378368@1606005131079/Worked-example-with-N3documentclass12ptminimal-usepackageamsmath_Q320.jpg)
![Sample graphical representation of OT∗\documentclass[12pt]{minimal}...](profile/Kim-Baraka/publication/340961211/figure/fig4/AS:960469288361984@1606005131209/Sample-graphical-representation-of-OTdocumentclass12ptminimal-usepackageamsmath_Q320.jpg)
Agents providing assistance to humans are faced with the challenge of automatically adjusting the level of assistance to ensure optimal performance. In this work, we argue that identifying the right level of assistance consists in balancing positive assistance outcomes and some (domain-dependent) measure of cost associated with assistive actions. T...
Document classification is ubiquitous in a business setting, but often the end users of a classifier are engaged in an ongoing feedback-retrain loop with the team that maintain it. We consider this feedback-retrain loop from a multi-agent point of view, considering the end users as autonomous agents that provide feedback on the labelled data provid...
Equity research analysts at financial institutions play a pivotal role in capital markets; they provide an efficient conduit between investors and companies' management and facilitate the efficient flow of information from companies, promoting functional and liquid markets. However, previous research in the academic finance and behavioral economics...
Link prediction, or the inference of future or missing connections between entities, is a well-studied problem in network analysis. A multitude of heuristics exist for link prediction in ordinary networks with a single type of connection. However, link prediction in multiplex networks, or networks with multiple types of connections, is not a well u...
The rapid growth in urban population poses significant challenges to moving city dwellers in a fast and convenient manner. This paper contributes to solving the challenges from the viewpoint of passengers by improving their on-vehicle experience. Specifically, we focus on the problem: Given an urban public transit network and a number of passengers...
Machine learning (especially reinforcement learning) methods for trading are increasingly reliant on simulation for agent training and testing. Furthermore, simulation is important for validation of hand-coded trading strategies and for testing hypotheses about market structure. A challenge, however, concerns the robustness of policies validated in...
Citations
... Embora iniciais, pode-se a partir dos experimentos constatar que quando o volume de dados é pequeno, não existe a necessidade de uso de bancos de dados de série temporais. Também o tipo de aplicação onde estão os dados de série temporais tem grande influência sobre a escolha do SGBD, conforme pode ser constatado em trabalhos como [Mostafa 2022] [Bamford 2023] [Wang 2023]. Assim, trabalhos futuros poderiam envolver a definição de cenários de uso específicos para os experimentos. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/870836424683522-1584634991874_Q64/Andrea-Coletta-2.jpg)
... Many current models in this domain use multimodal AI systems to predict trends and stock prices due to their effectiveness over numerical data. (Zeng et al. 2023) is one such work in which the authors introduced ViT-numspec MM-TSFM and showed that it outperformed other numerical and image-based models. Hence, we select daily stock price prediction task to assess various time-series forecasting models including two MM-TSFM that use ViT-numspec architecture. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/272474021560326-1441974277148_Q64/Zhen-Zeng-12.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/11431281122487360-1677393934457_Q64/Rachneet-Kaur-2.jpg)
... The well-known application domains of RL appear to be self-driving cars, robotics for industrial automation, business strategy planning, trading and finance, aircraft and robot motion control, healthcare, and gaming, among others [1,5,6]. In fact, research on RL has expanded in a variety of areas, making it a prominent topic in studies of AI, ML, multi-agent systems, and data science. ...
Reference: Why Reinforcement Learning?
![[object Object]](https://i1.rgstatic.net/ii/profile.image/590032838623232-1517686199031_Q64/Stephanie-Milani.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/279277321900032-1443596310198_Q64/Fei-Fang-18.jpg)
... Neural Networks) in the micro alphas' discovering process [60]. ...
... In this work we focus on efficiently learning multidimensional Hawkes processes, as accurate, fast and scalable optimization algorithms to enable a more widespread use of synthetic sequential events data that reflect dynamics observed in the real data. While in recent years a lot of focus has been devoted to Hawkes process variants that can capture more complex influence patters among events [9,10,11,12], efficient and scalable learning of Hawkes processes parameters have remained relatively under-examined. Especially, when a large number of event types is present in the data, algorithms which are naturally able to provide sparse solutions (i.e., identify that some event types may only influence the occurrence of a (small) subset of other events types in the future) in a fast runtime are needed. ...
... For example, the interested party might want to redesign the environment such that the agent is constrained to follow plans that keep certain relationships with some states. This can be beneficial in many planning settings, such as Anticipatory Planning (Burns et al. 2012), Counterplanning (Pozanco et al. 2018), Risk Avoidance and Management (Sohrabi et al. 2018), or Planning for Opportunities (Borrajo and Veloso 2021). Thus, we propose novel metrics that can be used to redesign environments for these other settings. ...
Reference: Generalising Planning Environment Redesign
![[object Object]](https://i1.rgstatic.net/ii/profile.image/273757814128642-1442280357229_Q64/Daniel-Borrajo.jpg)
... Note that at present, the Mivar technologies are being developed as a part of the research work on the creation of hybrid intelligent information systems (HIIS) [40] , using unstructured information [41] , metagraphs [42,43] , cognitive computer graphics [44] , neural net algorithms [45] , systems learning algorithms [46,47] , intellectual analysis methods [48] , and classical approaches to the development of multilevel systems [49] . Such an integrated approach makes it possible to solve a wide variety of practical problems in the AI field. ...
... An important aim of sequential decision optimization of challenging Discrete-Continuous Markov Decision Processes (DC-MDPs) in the artificial intelligence, operations research and control domains is to derive policies that achieve optimal control. A desirable property of such policies is compactness of representation, which provides efficient execution on resource-constrained systems such as mobile devices (Wang et al. 2022), as well as the potential for introspection and explanation (Topin et al. 2021). Moreover, while the derived policy is expected to perform well in expectation, in many applications it is desirable to obtain bounds on maximum policy error and and the scenarios that induce worst-case policy performance (Corso et al. 2021). ...
... Differentiable forward models in physics permit optimization and inference with very many parameters, and to incorporate flexible nonparametric models 18 jointly with deterministic physics. Autodiff has been used recently in optical and imaging science for phase retrieval and PSF modelling. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/385561320804352-1468936390255_Q64/Hector-Zenil.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/920513144713221-1596478844083_Q64/David-Krakauer-2.jpg)
... Document representation means representing the content and structure of a document in a new form, typically for the purpose of some downstream task. In the field of natural language processing, these representations are often vector embeddings constructed from a learned encoding function [20,24]. This type of document representation is useful in question answering and information retrieval. ...
