Early-exit networks are a class of dynamic neural networks designed for efficient inference by allowing models to make confident predictions at intermediate layers, rather than processing the full network. Early-exit mechanisms are methods for deep neural networks that add intermediate classifiers, allowing inference to stop at earlier layers for inputs assessed as low uncertainty. Decisions to exit are typically based on confidence measures such as softmax-derived scores, classification margins, or entropy-based criteria, with the goal of reducing computational cost. These approaches are commonly paired with specialized training procedures and system-level optimizations to improve efficiency while preserving accuracy. The main idea behind the technology is to stop excessive calculations when a good answer can already be given with a high degree of probability, which can save both computation and time. Early-exit networks have also been extended with expert-based exit criteria, where intermediate classifiers are treated as multiple “experts” whose predictions and confidence scores can be aggregated to decide whether to stop computation early. Hardware implementations are also being developed.
Transportation Economic Development Impact System
Transportation Economic Development Impact System (TREDIS) is an economic analysis system sold by consulting firm Economic Development Research Group that is used in planning major transportation investments in the US and Canada. The role of economic impact analysis and TREDIS in the transportation planning process is explained in guidebooks of the US Department of Transportation and the American Association of State Highway and Transportation Officials. TREDIS has been most commonly used for assessing the expected economic impacts of statewide highway programs, regional multi-modal plans and public transport investment. Its history and theoretical foundation are explained in peer reviewed journal articles. == How It Works == TREDIS has a series of modules that calculate different forms of impacts and benefits. One module is an accounting framework that calculates user benefits, including impacts on cargo transportation and commuting costs, based on transportation forecasting results. A second module calculates wider economic development benefits, including impacts on business productivity, economic development and multiplier effects from the input-output analysis. It applies an economic model to estimate impacts on jobs, income, gross regional product and business output, by sector of the economy. A third module applies cost-benefit analysis from alternative perspectives.
Predictive Model Markup Language
The Predictive Model Markup Language (PMML) is an XML-based predictive model interchange format conceived by Robert Lee Grossman, then the director of the National Center for Data Mining at the University of Illinois at Chicago. PMML provides a way for analytic applications to describe and exchange predictive models produced by data mining and machine learning algorithms. It supports common models such as logistic regression and other feedforward neural networks. Version 0.9 was published in 1998. Subsequent versions have been developed by the Data Mining Group. Since PMML is an XML-based standard, the specification comes in the form of an XML schema. PMML itself is a mature standard with over 30 organizations having announced products supporting PMML. == PMML components == A PMML file can be described by the following components: Header: contains general information about the PMML document, such as copyright information for the model, its description, and information about the application used to generate the model such as name and version. It also contains an attribute for a timestamp which can be used to specify the date of model creation. Data Dictionary: contains definitions for all the possible fields used by the model. It is here that a field is defined as continuous, categorical, or ordinal (attribute optype). Depending on this definition, the appropriate value ranges are then defined as well as the data type (such as, string or double). Data Transformations: transformations allow for the mapping of user data into a more desirable form to be used by the mining model. PMML defines several kinds of simple data transformations. Normalization: map values to numbers, the input can be continuous or discrete. Discretization: map continuous values to discrete values. Value mapping: map discrete values to discrete values. Functions (custom and built-in): derive a value by applying a function to one or more parameters. Aggregation: used to summarize or collect groups of values. Model: contains the definition of the data mining model. E.g., A multi-layered feedforward neural network is represented in PMML by a "NeuralNetwork" element which contains attributes such as: Model Name (attribute modelName) Function Name (attribute functionName) Algorithm Name (attribute algorithmName) Activation Function (attribute activationFunction) Number of Layers (attribute numberOfLayers) This information is then followed by three kinds of neural layers which specify the architecture of the neural network model being represented in the PMML document. These attributes are NeuralInputs, NeuralLayer, and NeuralOutputs. Besides neural networks, PMML allows for the representation of many other types of models including support vector machines, association rules, Naive Bayes classifier, clustering models, text models, decision trees, and different regression models. Mining Schema: a list of all fields used in the model. This can be a subset of the fields as defined in the data dictionary. It contains specific information about each field, such as: Name (attribute name): must refer to a field in the data dictionary Usage type (attribute usageType): defines the way a field is to be used in the model. Typical values are: active, predicted, and supplementary. Predicted fields are those whose values are predicted by the model. Outlier Treatment (attribute outliers): defines the outlier treatment to be use. In PMML, outliers can be treated as missing values, as extreme values (based on the definition of high and low values for a particular field), or as is. Missing Value Replacement Policy (attribute missingValueReplacement): if this attribute is specified then a missing value is automatically replaced by the given values. Missing Value Treatment (attribute missingValueTreatment): indicates how the missing value replacement was derived (e.g. as value, mean or median). Targets: allows for post-processing of the predicted value in the format of scaling if the output of the model is continuous. Targets can also be used for classification tasks. In this case, the attribute priorProbability specifies a default probability for the corresponding target category. It is used if the prediction logic itself did not produce a result. This can happen, e.g., if an input value is missing and there is no other method for treating missing values. Output: this element can be used to name all the desired output fields expected from the model. These are features of the predicted field and so are typically the predicted value itself, the probability, cluster affinity (for clustering models), standard error, etc. The latest release of PMML, PMML 4.1, extended Output to allow for generic post-processing of model outputs. In PMML 4.1, all the built-in and custom functions that were originally available only for pre-processing became available for post-processing too. == PMML 4.0, 4.1, 4.2 and 4.3 == PMML 4.0 was released on June 16, 2009. Examples of new features included: Improved Pre-Processing Capabilities: Additions to built-in functions include a range of Boolean operations and an If-Then-Else function. Time Series Models: New exponential Smoothing models; also place holders for ARIMA, Seasonal Trend Decomposition, and Spectral density estimation, which are to be supported in the near future. Model Explanation: Saving of evaluation and model performance measures to the PMML file itself. Multiple Models: Capabilities for model composition, ensembles, and segmentation (e.g., combining of regression and decision trees). Extensions of Existing Elements: Addition of multi-class classification for Support Vector Machines, improved representation for Association Rules, and the addition of Cox Regression Models. PMML 4.1 was released on December 31, 2011. New features included: New model elements for representing Scorecards, k-Nearest Neighbors (KNN) and Baseline Models. Simplification of multiple models. In PMML 4.1, the same element is used to represent model segmentation, ensemble, and chaining. Overall definition of field scope and field names. A new attribute that identifies for each model element if the model is ready or not for production deployment. Enhanced post-processing capabilities (via the Output element). PMML 4.2 was released on February 28, 2014. New features include: Transformations: New elements for implementing text mining New built-in functions for implementing regular expressions: matches, concat, and replace Simplified outputs for post-processing Enhancements to Scorecard and Naive Bayes model elements PMML 4.3 was released on August 23, 2016. New features include: New Model Types: Gaussian Process Bayesian Network New built-in functions Usage clarifications Documentation improvements Version 4.4 was released in November 2019. == Release history == == Data Mining Group == The Data Mining Group is a consortium managed by the Center for Computational Science Research, Inc., a nonprofit founded in 2008. The Data Mining Group also developed a standard called Portable Format for Analytics, or PFA, which is complementary to PMML.
International Journal of Pattern Recognition and Artificial Intelligence
The International Journal of Pattern Recognition and Artificial Intelligence was founded in 1987 and is published by World Scientific. The journal covers developments in artificial intelligence, and its sub-field, pattern recognition. This includes articles on image and language processing, robotics and neural networks. == Abstracting and indexing == The journal is abstracted and indexed in: SciSearch ISI Alerting Services CompuMath Citation Index Current Contents/Engineering, Computing & Technology Inspec io-port.net Compendex Computer Abstracts
Framework Convention on Artificial Intelligence
The Framework Convention on Artificial Intelligence and Human Rights, Democracy and the Rule of Law (also called Framework Convention on Artificial Intelligence or AI convention) is an international treaty on artificial intelligence. It was adopted under the auspices of the Council of Europe (CoE) and signed on 5 September 2024. The treaty aims to ensure that the development and use of AI technologies align with fundamental human rights, democratic values, and the rule of law, addressing risks such as misinformation, algorithmic discrimination, and threats to public institutions. More than 50 countries, including the EU member states, have endorsed the Framework Convention on Artificial Intelligence. == Background == The development of the Framework Convention on AI emerged in response to growing concerns over the ethical, legal, and societal impacts of artificial intelligence. The Council of Europe, which has historically played a key role in setting human rights standards across Europe, initiated discussions on AI governance in 2020, leading to the drafting of a binding legal framework. The process of creating the Framework Convention began in 2019 with the ad hoc Committee on Artificial Intelligence (CAHAI) assessing the feasibility of the instrument. In 2022, the Committee on Artificial Intelligence (CAI) took over the process, drafting and negotiating the text of the Convention. The treaty is designed to complement existing international human rights instruments, including the European Convention on Human Rights and the Convention for the Protection of Individuals with regard to Automatic Processing of Personal Data. == Structure and content == The Convention establishes fundamental principles for AI governance, including transparency, accountability, non-discrimination, and human rights protection through eight chapters and 26 articles. Adopted in 2024, this landmark treaty addresses AI governance through seven core principles and detailed implementation mechanisms. It mandates risk and impact assessments to mitigate potential harms and provides safeguards such as the right to challenge AI-driven decisions. It applies to public authorities and private entities acting on their behalf but excludes national security and defense activities. Implementation is overseen by a Conference of the Parties, ensuring compliance and international cooperation. Activities within the AI system lifecycle must adhere to seven fundamental principles, ensuring compliance with human rights, democracy, and the rule of law. The treaty also establishes remedies, procedural rights and safeguards, and risk and impact management requirements to promote accountability, transparency, and responsible AI development. The treaty consists of five chapters. Chapter I contains general provisions. Chapter II states the general obligation to protect human rights and the integrity of democratic processes and respect of the rule of law. The main principles and rights are contained in Chapter III, which consists of Articles 6 to 13. Chapter IV (Articles 14 to 15) sets up the legal remedies. Chapter V states the risk and impact management framework. Chapter VI facilitates the implementation criteria of the treaty. Chapter VII sets the co-operation and oversight mechanisms. Chapter VIII contains various concluding clauses. Article 1 declares the objectives of the treaty, to ensure that activities within the lifecycle of artificial intelligence systems are fully consistent with human rights, democracy and the rule of law. == Entry into force == The treaty will enter into force on the first day of the month following the expiration of a period of three months after the date on which five ratification made by five countries, including three member states of the Council of Europe. == Competing approaches == While the CoE's AI Convention represents a multilateral effort to regulate AI through a human rights-based approach, alternative frameworks have also been proposed. One notable example is the Munich Draft for a Convention on AI, Data and Human Rights, an initiative led by legal scholars and policymakers in Germany. The Munich Draft advocates for stronger safeguards against AI-related risks, emphasizing stricter data protection measures, accountability for AI developers, and explicit prohibitions on high-risk AI applications, such as mass surveillance and autonomous lethal weapons. Unlike the CoE convention, which focuses on balancing innovation with regulation, the Munich Draft takes a more precautionary stance, calling for tighter controls over AI deployment in sensitive domains. Other competing international efforts include the OECD’s AI Principles, the GPAI (Global Partnership on AI), and the European Union's AI Act, each of which offers different regulatory strategies to govern AI at regional and global levels. == Signatories == Signatories include Andorra, Canada, the European Union, Georgia, Iceland, Israel, Japan, Liechtenstein, the Republic of Moldova, Montenegro, Norway, San Marino, Switzerland, Ukraine, the United Kingdom, the United States, and Uruguay. == Endorsement == The treaty was widely endorsed by leading AI policy experts, including Stuart J. Russell, Virginia Dignum, Emma Ruttkamp-Bloem, Pascal Pichonnaz, Maria Helen Murphy, Angella Ndaka, Hannes Werthner, Katja Langenbucher, Gry Hasselbalch, Ricardo Baeza-Yates, Kutoma Wakunuma, Gianclaudio Malgieri, Oreste Pollicino, Nagla Rizk, Giovanni Sartor, Lee Tiedrich, Ingrid Schneider, Eduardo Bertoni, Garry Kasparov, Merve Hikcok, and Marc Rotenberg. The treaty was also endorsed by notable political leaders, including Theodoros Roussopoulos, President of the Parliamentart Assembly in the Council of Europe, and Christopher Holmes, Member of the House of Lords of the United Kingdom, and by the International Bar Association (IBA), and personally by Almudena Arpón de Mendívil, President of the IBA. The Center for AI and Digital Policy (CAIDP) has been carrying out a campaign to promote endorsement of the treaty by urging various countries to sign and ratify the treaty. The CAIDP further urged the countries to make a clear and firm commitment to ensure the full inclusion of the private sector under the treaty’s provisions.
Catie Cuan
Catie Cuan is an artist, entrepeuneur, and innovator in the field of robotic art and human-robot interaction, where she specializes in choreorobotics, an emerging field at the intersection of choreographic dance and robotics. Catie Cuan is currently one of the academic researchers pioneering the field of choreorobotics and currently holds a post-doctoral fellowship at Stanford University. == Career == Catie Cuan earned a bachelor's degree from the University of California, Berkeley. She graduated with a Ph.D. from the Department of Mechanical Engineering at Stanford University, focusing in robotics. Her most cited publication is about how to improve robotic expressive systems using tools from dance theory, such as the Laban/Bartenieff Movement Analysis. In her most recent research projects, she explores a predictive model of imitation learning for robots moving around humans, a project that advances the field of social robotics. Cuan credits her work in robotics to the experience with her father when he had a stroke and was surrounded by many medical machines, which made her think about how people might feel empowered and hopeful rather than afraid. As a ballet dancer and choreographer, she has performed with the Metropolitan Opera Ballet and the Lyric Opera of Chicago. In 2020, she was the dancer and choreographer of the show Output, which was part of a collaboration with ThoughtWorks Arts and the Pratt Institute. In the production, she danced with an ABB IRB 6700 industrial robot. In 2022, she was named as an IF/THEN ambassador for the American Association for the Advancement of Science. The same year, she was appointed Futurist-in-Residence at the Smithsonian Arts and Industries Building, where she performed at the closing ceremonies of the FUTURES exhibit on July 6, 2022. Cuan has also contributed to product designs, working with IDEO and Dutch interior design firm moooi on their Piro project, which launched a dancing scent diffuser robot during Milan Design Week in June 2022. She is a TED speaker with talks about how to teach robots to dance, and what is coming up for dancing robots in the AI era.
Ethics of artificial intelligence
The ethics of artificial intelligence covers a broad range of topics within AI that are considered to have particular ethical stakes. This includes algorithmic biases, fairness, accountability, transparency, privacy, and regulation, particularly where systems influence or automate human decision-making. It also covers various emerging or potential future challenges such as machine ethics (how to make machines that behave ethically), lethal autonomous weapon systems, arms race dynamics, AI safety and alignment, technological unemployment, AI-enabled misinformation, how to treat certain AI systems if they have a moral status (AI welfare and rights), artificial superintelligence and existential risks. Some application areas may also have particularly important ethical implications, like healthcare, education, criminal justice, or the military. == Machine ethics == Machine ethics (or machine morality) is the field of research concerned with designing Artificial Moral Agents (AMAs), robots or artificially intelligent computers that behave morally or as though moral. To account for the nature of these agents, it has been suggested to consider certain philosophical ideas, like the standard characterizations of agency, rational agency, moral agency, and artificial agency, which are related to the concept of AMAs. There are discussions on creating tests to see if an AI is capable of making ethical decisions. Alan Winfield concludes that the Turing test is flawed and the requirement for an AI to pass the test is too low. A proposed alternative test is one called the Ethical Turing Test, which would improve on the current test by having multiple judges decide if the AI's decision is ethical or unethical. Neuromorphic AI could be one way to create morally capable robots, as it aims to process information similarly to humans, nonlinearly and with millions of interconnected artificial neurons. Similarly, whole-brain emulation (scanning a brain and simulating it on digital hardware) could also in principle lead to human-like robots, thus capable of moral actions. And large language models are capable of approximating human moral judgments. Inevitably, this raises the question of the environment in which such robots would learn about the world and whose morality they would inherit – or if they end up developing human 'weaknesses' as well: selfishness, pro-survival attitudes, inconsistency, scale insensitivity, etc. In Moral Machines: Teaching Robots Right from Wrong, Wendell Wallach and Colin Allen conclude that attempts to teach robots right from wrong will likely advance understanding of human ethics by motivating humans to address gaps in modern normative theory and by providing a platform for experimental investigation. As one example, it has introduced normative ethicists to the controversial issue of which specific learning algorithms to use in machines. For simple decisions, Nick Bostrom and Eliezer Yudkowsky have argued that decision trees (such as ID3) are more transparent than neural networks and genetic algorithms, while Chris Santos-Lang argued in favor of machine learning on the grounds that the norms of any age must be allowed to change and that natural failure to fully satisfy these particular norms has been essential in making humans less vulnerable to criminal "hackers". Some researchers frame machine ethics as part of the broader AI control or value alignment problem: the difficulty of ensuring that increasingly capable systems pursue objectives that remain compatible with human values and oversight. Stuart Russell has argued that beneficial systems should be designed to (1) aim at realizing human preferences, (2) remain uncertain about what those preferences are, and (3) learn about them from human behaviour and feedback, rather than optimizing a fixed, fully specified goal. Some authors argue that apparent compliance with human values may reflect optimization for evaluation contexts rather than stable internal norms, complicating the assessment of alignment in advanced language models. == Challenges == === Algorithmic biases === AI has become increasingly inherent in facial and voice recognition systems. These systems may be vulnerable to biases and errors introduced by their human creators. Notably, the data used to train them can have biases. According to Allison Powell, associate professor at LSE and director of the Data and Society programme, data collection is never neutral and always involves storytelling. She argues that the dominant narrative is that governing with technology is inherently better, faster and cheaper, but proposes instead to make data expensive, and to use it both minimally and valuably, with the cost of its creation factored in. Friedman and Nissenbaum identify three categories of bias in computer systems: existing bias, technical bias, and emergent bias. In natural language processing, problems can arise from the text corpus—the source material the algorithm uses to learn about the relationships between different words. Large companies such as IBM, Google, etc. that provide significant funding for research and development have made efforts to research and address these biases. One potential solution is to create documentation for the data used to train AI systems. Process mining can be an important tool for organizations to achieve compliance with proposed AI regulations by identifying errors, monitoring processes, identifying potential root causes for improper execution, and other functions. However, there are also limitations to the current landscape of fairness in AI, due to the intrinsic ambiguities in the concept of discrimination, both at the philosophical and legal level. ==== Racial and gender biases ==== Bias can be introduced through historical data used to train AI systems. For instance, Amazon terminated their use of AI hiring and recruitment because the algorithm favored male candidates over female ones. This was because Amazon's system was trained with data collected over a 10-year period that included mostly male candidates. The algorithms learned the biased pattern from the historical data, and generated predictions where these types of candidates were most likely to succeed in getting the job. Therefore, the recruitment decisions made by the AI system turned out to be biased against female and minority candidates. The performance of facial recognition and computer vision models may vary based on race and gender. Facial recognition algorithms made by Microsoft, IBM and Face++ all performed significantly worse on darker-skinned women. Facial recognition was shown to be biased against those with darker skin tones. AI systems may be less accurate for black people, as was the case in the development of an AI-based pulse oximeter that overestimated blood oxygen levels in patients with darker skin, causing issues with their hypoxia treatment. In 2015, controversy erupted after a Black couple were labeled "Gorillas" by Google Photos. Oftentimes the systems are able to easily detect the faces of white people while being unable to register the faces of people who are black. This has led to the ban of police usage of AI materials or software in some U.S. states. The reason for these biases is that AI pulls information from across the internet to influence its responses in each situation. For example, if a facial recognition system was only tested on people who were white, it would make it much harder for it to interpret the facial structure and tones of other races and ethnicities. Biases often stem from the training data rather than the algorithm itself, notably when the data represents past human decisions. A 2020 study that reviewed voice recognition systems from Amazon, Apple, Google, IBM, and Microsoft found that they have higher error rates when transcribing black people's voices than white people's. Injustice in the use of AI is much harder to eliminate within healthcare systems, as oftentimes diseases and conditions can affect different races and genders differently. This can lead to confusion as the AI may be making decisions based on statistics showing that one patient is more likely to have problems due to their gender or race. This can be perceived as a bias because each patient is a different case, and AI is making decisions based on what it is programmed to group that individual into. This leads to a discussion about what should be considered a biased decision in the distribution of treatment. While it is known that there are differences in how diseases and injuries affect different genders and races, there is a discussion on whether it is fairer to incorporate this into healthcare treatments, or to examine each patient without this knowledge. In modern society there are certain tests for diseases, such as breast cancer, that are recommended to certain groups of people over others because they are more likely to contract the disease in question. If AI implements these statistics