The machine learning community currently has no standardized process for documenting datasets. To address this gap, we propose datasheets for datasets. In the electronics industry, every component, no matter how simple or complex, is accompanied with a datasheet that describes its operating characteristics, test results, recommended uses, and other information. By analogy, we propose that every dataset be accompanied with a datasheet that documents its motivation, composition, collection process, recommended uses, and so on. Datasheets for datasets will facilitate better communication between dataset creators and dataset consumers, and encourage the machine learning community to prioritize transparency and accountability. Read More
Tag Archives: Explainability
Measurable Counterfactual Local Explanations for Any Classifier
We propose a novel method for explaining the predictions of any classifier. In our approach, local explanations are expected to explain both the outcome of a prediction and how that prediction would change if ’things had been different’. Furthermore, we argue that satisfactory explanations cannot be dissociated from a notion and measure of fidelity, as advocated in the early days of neural networks’ knowledge extraction. We introduce a definition of fidelity to the underlying classifier for local explanation models which is based on distances to a target decision boundary. A system called CLEAR: Counterfactual Local Explanations via Regression, is introduced and evaluated. CLEAR generates w-counterfactual explanations that state minimum changes necessary to flip a prediction’s classification. CLEAR then builds local regression models, using the w-counterfactuals to measure and improve the fidelity of its regressions. By contrast, the popular LIME method [15],which also uses regression to generate local explanations, neither measures its own fidelity nor generates counterfactuals. CLEAR’s regressions are found to have significantly higher fidelity than LIME’s, averaging over 45% higher in this paper’s four case studies. Read More
Please Stop Explaining Black Box Models for High-Stakes Decisions
Black box machine learning models are currently being used for high stakes decision-making throughout society, causing problems throughout healthcare, criminal justice, and in other domains. People have hoped that creating methods for explaining these black box models will alleviate some of these problems, but trying to explain black box models, rather than creating models that are interpretable in the first place, is likely to perpetuate bad practices and can potentially cause catastrophic harm to society. There is a way forward – it is to design models that are inherently interpretable. Read More
Intellectual Debt: With Great Power Comes Great Ignorance
What Technical Debt Can Teach Us About the Dangers of AI Working Too Well.
Harvard Professor Jonathan Zittrain uses technical debt to help understand “intellectual debt”: the idea that things work, even though we don’t understand precisely how. He points out that “While machine learning systems can surpass humans at pattern recognition and predictions, they generally cannot explain their answers in human-comprehensible terms.”
Why is this a problem? Because, “as AI’s intellectual debt piles up: the coming pervasiveness of machine learning models. Taken in isolation, oracular answers can generate consistently helpful results. But these systems won’t stay in isolation. As AI systems gather and ingest the world’s data, they’ll produce data of their own — much of which will be taken up by still other AI systems.” Read More
AI ‘emotion recognition’ can’t be trusted
As artificial intelligence is used to make more decisions about our lives, engineers have sought out ways to make it more emotionally intelligent. That means automating some of the emotional tasks that come naturally to humans — most notably, looking at a person’s face and knowing how they feel.
To achieve this, tech companies like Microsoft, IBM, and Amazon all sell what they call “emotion recognition” algorithms, which infer how people feel based on facial analysis. For example, if someone has a furrowed brow and pursed lips, it means they’re angry. If their eyes are wide, their eyebrows are raised, and their mouth is stretched, it means they’re afraid, and so on.
But the belief that we can easily infer how people feel based on how they look is controversial, and a significant new review of the research suggests there’s no firm scientific justification for it. Read More
Machine Learning Interpretability: Do You Know What Your Model Is Doing?
Machine learning has a great potential to improve data products and business processes. It is used to propose products and news articles that we might be interested in as well as to steer autonomous vehicles and to challenge human experts in non-trivial games. Although machine learning models perform extraordinary well in solving those tasks, we need to be aware of the latent risks that arise through inadvertently encoding bias, responsible for discriminating individuals and strengthening preconceptions, or mistakenly taking random correlation for causation. In her book „Weapons of Math Destruction“, Cathy O’Neil even went so far as to say that improvident use of algorithms can perpetuate inequality and threaten democracy. Filter bubbles, racist chat bots, and foolable face detection are prominent examples of malicious outcomes of learning algorithms. With great power comes great responsibility—wise words that every practitioner should keep in mind. Read More
Using the ‘What-If Tool’ to investigate Machine Learning models.
In this era of explainable and interpretable Machine Learning, one merely cannot be content with simply training the model and obtaining predictions from it. To be able to really make an impact and obtain good results, we should also be able to probe and investigate our models. Apart from that, algorithmic fairness constraints and bias should also be clearly kept in mind before going ahead with the model.
Investigating a model requires asking a lot of questions and one needs to have an acumen of a detective to probe and look for issues and inconsistencies within the models. Also, such a task is usually complex requiring to write a lot of custom code. Fortunately, the What-If Tool has been created to address this issue making it easier for a broad set of people to examine, evaluate, and debug ML systems easily and accurately. Read More
Putting neural networks under the microscope
Researchers from MIT and the Qatar Computing Research Institute (QCRI) are putting the machine-learning systems known as neural networks under the microscope.
In a study that sheds light on how these systems manage to translate text from one language to another, the researchers developed a method that pinpoints individual nodes, or “neurons,” in the networks that capture specific linguistic features.
Neural networks learn to perform computational tasks by processing huge sets of training data. In machine translation, a network crunches language data annotated by humans, and presumably “learns” linguistic features, such as word morphology, sentence structure, and word meaning. Given new text, these networks match these learned features from one language to another, and produce a translation. Read More
AI agent offers rationales using everyday language to explain its actions
Georgia Institute of Technology researchers, in collaboration with Cornell University and University of Kentucky, have developed an artificially intelligent (AI) agent that can automatically generate natural language explanations in real-time to convey the motivations behind its actions.
The work is designed to give humans engaging with AI agents or robots confidence that the agent is performing the task correctly and can explain a mistake or errant behavior.The agent also uses everyday language that non-experts can understand. The explanations, or “rationales” as the researchers call them, are designed to be relatable and inspire trust in those who might be in the workplace with AI machines or interact with them in social situations. Read More
Rick's Cafe AI 