arXiv subjects

Melanie Mitchell

Publications and source records attributed to Melanie Mitchell.

34 records · Page 2Linked to original sources

arXiv2021

Frontiers in Evolutionary Computation: A Workshop Report

In July of 2021, the Santa Fe Institute hosted a workshop on evolutionary computation as part of its Foundations of Intelligence in Natural and Artificial Systems project. This project seeks to advance the field of artificial intelligence by promoting interdisciplinary research on the nature of intelligence. The workshop brought together computer scientists and biologists to share their insights about the nature of evolution and the future of evolutionary computation. In this report, we summarize each of the talks and the subsequent discussions. We also draw out a number of key themes and identify important frontiers for future research.

cs.NE↗

arXiv2021

Abstraction and Analogy-Making in Artificial Intelligence

Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains. Despite of a long history of research on constructing AI systems with these abilities, no current AI system is anywhere close to a capability of forming humanlike abstractions or analogies. This paper reviews the advantages and limitations of several approaches toward this goal, including symbolic methods, deep learning, and probabilistic program induction. The paper concludes with several proposals for designing challenge tasks and evaluation measures in order to make quantifiable and generalizable progress in this area.

cs.AI↗

arXiv2021

Foundations of Intelligence in Natural and Artificial Systems: A Workshop Report

In March of 2021, the Santa Fe Institute hosted a workshop as part of its Foundations of Intelligence in Natural and Artificial Systems project. This project seeks to advance the field of artificial intelligence by promoting interdisciplinary research on the nature of intelligence. During the workshop, speakers from diverse disciplines gathered to develop a taxonomy of intelligence, articulating their own understanding of intelligence and how their research has furthered that understanding. In this report, we summarize the insights offered by each speaker and identify the themes that emerged during the talks and subsequent discussions.

cs.AI↗

arXiv2021

Why AI is Harder Than We Think

Since its beginning in the 1950s, the field of artificial intelligence has cycled several times between periods of optimistic predictions and massive investment ("AI spring") and periods of disappointment, loss of confidence, and reduced funding ("AI winter"). Even with today's seemingly fast pace of AI breakthroughs, the development of long-promised technologies such as self-driving cars, housekeeping robots, and conversational companions has turned out to be much harder than many people expected. One reason for these repeating cycles is our limited understanding of the nature and complexity of intelligence itself. In this paper I describe four fallacies in common assumptions made by AI researchers, which can lead to overconfident predictions about the field. I conclude by discussing the open questions spurred by these fallacies, including the age-old challenge of imbuing machines with humanlike common sense.

cs.AI↗

arXiv2021

Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers

Neural networks trained on visual data are well-known to be vulnerable to often imperceptible adversarial perturbations. The reasons for this vulnerability are still being debated in the literature. Recently Ilyas et al. (2019) showed that this vulnerability arises, in part, because neural network classifiers rely on highly predictive but brittle "non-robust" features. In this paper we extend the work of Ilyas et al. by investigating the nature of the input patterns that give rise to these features. In particular, we hypothesize that in a neural network trained in a standard way, non-robust features respond to small, "non-semantic" patterns that are typically entangled with larger, robust patterns, known to be more human-interpretable, as opposed to solely responding to statistical artifacts in a dataset. Thus, adversarial examples can be formed via minimal perturbations to these small, entangled patterns. In addition, we demonstrate a corollary of our hypothesis: robust classifiers are more effective than standard (non-robust) ones as a source for generating transferable adversarial examples in both the untargeted and targeted settings. The results we present in this paper provide new insight into the nature of the non-robust features responsible for adversarial vulnerability of neural network classifiers.

cs.LG↗

arXiv2020

Next Wave Artificial Intelligence: Robust, Explainable, Adaptable, Ethical, and Accountable

The history of AI has included several "waves" of ideas. The first wave, from the mid-1950s to the 1980s, focused on logic and symbolic hand-encoded representations of knowledge, the foundations of so-called "expert systems". The second wave, starting in the 1990s, focused on statistics and machine learning, in which, instead of hand-programming rules for behavior, programmers constructed "statistical learning algorithms" that could be trained on large datasets. In the most recent wave research in AI has largely focused on deep (i.e., many-layered) neural networks, which are loosely inspired by the brain and trained by "deep learning" methods. However, while deep neural networks have led to many successes and new capabilities in computer vision, speech recognition, language processing, game-playing, and robotics, their potential for broad application remains limited by several factors. A concerning limitation is that even the most successful of today's AI systems suffer from brittleness-they can fail in unexpected ways when faced with situations that differ sufficiently from ones they have been trained on. This lack of robustness also appears in the vulnerability of AI systems to adversarial attacks, in which an adversary can subtly manipulate data in a way to guarantee a specific wrong answer or action from an AI system. AI systems also can absorb biases-based on gender, race, or other factors-from their training data and further magnify these biases in their subsequent decision-making. Taken together, these various limitations have prevented AI systems such as automatic medical diagnosis or autonomous vehicles from being sufficiently trustworthy for wide deployment. The massive proliferation of AI across society will require radically new ideas to yield technology that will not sacrifice our productivity, our quality of life, or our values.

cs.CY↗

arXiv2019

Revisiting Visual Grounding

We revisit a particular visual grounding method: the "Image Retrieval Using Scene Graphs" (IRSG) system of Johnson et al. (2015). Our experiments indicate that the system does not effectively use its learned object-relationship models. We also look closely at the IRSG dataset, as well as the widely used Visual Relationship Dataset (VRD) that is adapted from it. We find that these datasets exhibit biases that allow methods that ignore relationships to perform relatively well. We also describe several other problems with the IRSG dataset, and report on experiments using a subset of the dataset in which the biases and other problems are removed. Our studies contribute to a more general effort: that of better understanding what machine learning methods that combine language and vision actually learn and what popular datasets actually test.

cs.CV↗

arXiv2018

An interview based study of pioneering experiences in teaching and learning Complex Systems in Higher Education

Due to the interdisciplinary nature of complex systems as a field, students studying complex systems at University level have diverse disciplinary backgrounds. This brings challenges (e.g. wide range of computer programming skills) but also opportunities (e.g. facilitating interdisciplinary interactions and projects) for the classroom. However, there is little published regarding how these challenges and opportunities are handled in teaching and learning Complex Systems as an explicit subject in higher education, and how this differs in comparison to other subject areas. We seek to explore these particular challenges and opportunities via an interview-based study of pioneering teachers and learners (conducted amongst the authors) regarding their experiences. We compare and contrast those experiences, and analyse them with respect to the educational literature. Our discussions explored: approaches to curriculum design, how theories/models/frameworks of teaching and learning informed decisions and experience, how diversity in student backgrounds was addressed, and assessment task design. We found a striking level of commonality in the issues expressed as well as the strategies to handle them, for example a significant focus on problem-based learning, and the use of major student-led creative projects for both achieving and assessing learning outcomes.

physics.ed-ph↗

arXiv2017

Sparse Coding on Stereo Video for Object Detection

Deep Convolutional Neural Networks (DCNN) require millions of labeled training examples for image classification and object detection tasks, which restrict these models to domains where such datasets are available. In this paper, we explore the use of unsupervised sparse coding applied to stereo-video data to help alleviate the need for large amounts of labeled data. We show that replacing a typical supervised convolutional layer with an unsupervised sparse-coding layer within a DCNN allows for better performance on a car detection task when only a limited number of labeled training examples is available. Furthermore, the network that incorporates sparse coding allows for more consistent performance over varying initializations and ordering of training examples when compared to a fully supervised DCNN. Finally, we compare activations between the unsupervised sparse-coding layer and the supervised convolutional layer, and show that the sparse representation exhibits an encoding that is depth selective, whereas encodings from the convolutional layer do not exhibit such selectivity. These result indicates promise for using unsupervised sparse-coding approaches in real-world computer vision tasks in domains with limited labeled training data.

cs.CV↗

arXiv2017

Semantic Image Retrieval via Active Grounding of Visual Situations

We describe a novel architecture for semantic image retrieval---in particular, retrieval of instances of visual situations. Visual situations are concepts such as "a boxing match," "walking the dog," "a crowd waiting for a bus," or "a game of ping-pong," whose instantiations in images are linked more by their common spatial and semantic structure than by low-level visual similarity. Given a query situation description, our architecture---called Situate---learns models capturing the visual features of expected objects as well the expected spatial configuration of relationships among objects. Given a new image, Situate uses these models in an attempt to ground (i.e., to create a bounding box locating) each expected component of the situation in the image via an active search procedure. Situate uses the resulting grounding to compute a score indicating the degree to which the new image is judged to contain an instance of the situation. Such scores can be used to rank images in a collection as part of a retrieval system. In the preliminary study described here, we demonstrate the promise of this system by comparing Situate's performance with that of two baseline methods, as well as with a related semantic image-retrieval system based on "scene graphs."

cs.CV↗

arXiv2017

Gaussian Processes with Context-Supported Priors for Active Object Localization

We devise an algorithm using a Bayesian optimization framework in conjunction with contextual visual data for the efficient localization of objects in still images. Recent research has demonstrated substantial progress in object localization and related tasks for computer vision. However, many current state-of-the-art object localization procedures still suffer from inaccuracy and inefficiency, in addition to failing to provide a principled and interpretable system amenable to high-level vision tasks. We address these issues with the current research. Our method encompasses an active search procedure that uses contextual data to generate initial bounding-box proposals for a target object. We train a convolutional neural network to approximate an offset distance from the target object. Next, we use a Gaussian Process to model this offset response signal over the search space of the target. We then employ a Bayesian active search for accurate localization of the target. In experiments, we compare our approach to a state-of-theart bounding-box regression method for a challenging pedestrian localization task. Our method exhibits a substantial improvement over this baseline regression method.

cs.CV↗

arXiv2016

Fast On-Line Kernel Density Estimation for Active Object Localization

A major goal of computer vision is to enable computers to interpret visual situations---abstract concepts (e.g., "a person walking a dog," "a crowd waiting for a bus," "a picnic") whose image instantiations are linked more by their common spatial and semantic structure than by low-level visual similarity. In this paper, we propose a novel method for prior learning and active object localization for this kind of knowledge-driven search in static images. In our system, prior situation knowledge is captured by a set of flexible, kernel-based density estimations---a situation model---that represent the expected spatial structure of the given situation. These estimations are efficiently updated by information gained as the system searches for relevant objects, allowing the system to use context as it is discovered to narrow the search. More specifically, at any given time in a run on a test image, our system uses image features plus contextual information it has discovered to identify a small subset of training images---an importance cluster---that is deemed most similar to the given test image, given the context. This subset is used to generate an updated situation model in an on-line fashion, using an efficient multipole expansion technique. As a proof of concept, we apply our algorithm to a highly varied and challenging dataset consisting of instances of a "dog-walking" situation. Our results support the hypothesis that dynamically-rendered, context-based probability models can support efficient object localization in visual situations. Moreover, our approach is general enough to be applied to diverse machine learning paradigms requiring interpretable, probabilistic representations generated from partially observed data.

cs.CV↗

arXiv2016

Active Object Localization in Visual Situations

We describe a method for performing active localization of objects in instances of visual situations. A visual situation is an abstract concept---e.g., "a boxing match", "a birthday party", "walking the dog", "waiting for a bus"---whose image instantiations are linked more by their common spatial and semantic structure than by low-level visual similarity. Our system combines given and learned knowledge of the structure of a particular situation, and adapts that knowledge to a new situation instance as it actively searches for objects. More specifically, the system learns a set of probability distributions describing spatial and other relationships among relevant objects. The system uses those distributions to iteratively sample object proposals on a test image, but also continually uses information from those object proposals to adaptively modify the distributions based on what the system has detected. We test our approach's ability to efficiently localize objects, using a situation-specific image dataset created by our group. We compare the results with several baselines and variations on our method, and demonstrate the strong benefit of using situation knowledge and active context-driven localization. Finally, we contrast our method with several other approaches that use context as well as active search for object localization in images.

cs.CV↗

arXiv1999

Resource Sharing and Coevolution in Evolving Cellular Automata

Evolving one-dimensional cellular automata (CAs) with genetic algorithms has provided insight into how improved performance on a task requiring global coordination emerges when only local interactions are possible. Two approaches that can affect the search efficiency of the genetic algorithm are coevolution, in which a population of problems---in our case, initial configurations of the CA lattice---evolves along with the population of CAs; and resource sharing, in which a greater proportion of a limited fitness resource is assigned to those CAs which correctly solve problems that fewer other CAs in the population can solve. Here we present evidence that, in contrast to what has been suggested elsewhere, the improvements observed when both techniques are used together depend largely on resource sharing alone.

adap-org↗

arXiv1998

The Evolutionary Design of Collective Computation in Cellular Automata

We investigate the ability of a genetic algorithm to design cellular automata that perform computations. The computational strategies of the resulting cellular automata can be understood using a framework in which ``particles'' embedded in space-time configurations carry information and interactions between particles effect information processing. This structural analysis can also be used to explain the evolutionary process by which the strategies were designed by the genetic algorithm. More generally, our goals are to understand how machine-learning processes can design complex decentralized systems with sophisticated collective computational abilities and to develop rigorous frameworks for understanding how the resulting dynamical systems perform computation.

adap-org↗

arXiv1993

Revisiting the Edge of Chaos: Evolving Cellular Automata to Perform Computations

We present results from an experiment similar to one performed by Packard (1988), in which a genetic algorithm is used to evolve cellular automata (CA) to perform a particular computational task. Packard examined the frequency of evolved CA rules as a function of Langton's lambda parameter (Langton, 1990), and interpreted the results of his experiment as giving evidence for the following two hypotheses: (1) CA rules able to perform complex computations are most likely to be found near ``critical'' lambda values, which have been claimed to correlate with a phase transition between ordered and chaotic behavioral regimes for CA; (2) When CA rules are evolved to perform a complex computation, evolution will tend to select rules with lambda values close to the critical values. Our experiment produced very different results, and we suggest that the interpretation of the original results is not correct. We also review and discuss issues related to lambda, dynamical-behavior classes, and computation in CA. The main constructive results of our study are identifying the emergence and competition of computational strategies and analyzing the central role of symmetries in an evolutionary system. In particular, we demonstrate how symmetry breaking can impede the evolution toward higher computational capability.

adap-org↗