7:00 – 6:00 ASRC GOES
Check Copenhagen Wheel serial number for this recall
Contact Dreamhost about missing folders – done
- GSAW prep
- Tix and hotel – done
- TF Dev Conf
- Tix, car, and hotel – done
- Met with Vadim
- Need to write up a monthly plan for Erik for the sim
- GPT-2 Agents
An ant colony has memories that its individual members don’t have
- Like a brain, an ant colony operates without central control. Each is a set of interacting individuals, either neurons or ants, using simple chemical interactions that in the aggregate generate their behaviour. People use their brains to remember. Can ant colonies do that?
7:00 – ASRC
- More edits
- Changed all the overviews so that they also reference the section by name. It reads better now, I think
- Meeting with Thom
- GPT-2 Agents
- GSAW Slide deck
I got invited to the TF Dev conference!
The HKS Misinformation Review is a new format of peer-reviewed, scholarly publication. Content is produced and “fast-reviewed” by misinformation scientists and scholars, released under open access, and geared towards emphasizing real-world implications. All content is targeted towards a specialized audience of researchers, journalists, fact-checkers, educators, policy makers, and other practitioners working in the information, media, and platform landscape.
- For the essays, a length of 1,500 to 3,000 words (excluding footnotes and methodology appendix) is appropriate, but the HKS Misinformation Review will consider and publish longer articles. Authors of articles with more than 3,000 words should consult the journal’s editors before submission.
7:00 – ASRC GOES
- It looks like I fixed my LaTeX problems. I went to C:\Users\phil\AppData\Roaming\MiKTeX\2.9\tex\latex, and deleted the ifvtex folder. Re-ran, things installed, and all is better now
- Pinged Isaac about the idea of creating scenarios that incorporate the NASA simulators
- Speakers presenting in a plenary session are scheduled to speak for 15 minutes, with five additional minutes allowed for questions and answers from the audience
- Our microphones work best when the antenna unit is clipped to a belt and the microphone is attached near the center of your chest.
- We are NOT providing network capabilities such as WiFi. If you require WiFi, you are responsible for purchasing it from the hotel and ensuring that it works for the presentation.
- Charts produced by the PC version of Microsoft PowerPoint 2013, 2016 or 365 are preferred
- . In creating your slides, note that the presentation room is large and you should consider this in your selection of larger fonts, diagram size, etc. At a minimum, a 20-point font is recommended
- GPT-2 – Maybe do something with Aaron today?
7:00 – 7:00 ASRC Research
- 1st International Conference on Autonomic Computing and Self-Organizing Systems – ACSOS 2020
- Washington DC from August 17 to August 21, 2020
- Important Dates (tentative)
- April 1, 2020: Abstract submission deadline
- April 8, 2020: Paper submission deadline
- June 8, 2020: Notification to authors
- July 8, 2020: Camera Ready Deadline
- Starting on Ethics
- A Framework for Making Ethical Decisions
- Decisions about right and wrong permeate everyday life. Ethics should concern all levels of life: acting properly as individuals, creating responsible organizations and governments, and making our society as a whole more ethical. This document is designed as an introduction to making ethical decisions. It recognizes that decisions about “right” and “wrong” can be difficult, and may be related to individual context. It first provides a summary of the major sources for ethical thinking, and then presents a framework for decision-making.
- Archipelago-Wide Island Restoration in the Galápagos Islands: Reducing Costs of Invasive Mammal Eradication Programs and Reinvasion Risk
- Invasive alien mammals are the major driver of biodiversity loss and ecosystem degradation on islands. Over the past three decades, invasive mammal eradication from islands has become one of society’s most powerful tools for preventing extinction of insular endemics and restoring insular ecosystems. As practitioners tackle larger islands for restoration, three factors will heavily influence success and outcomes: the degree of local support, the ability to mitigate for non-target impacts, and the ability to eradicate non-native species more cost-effectively. Investments in removing invasive species, however, must be weighed against the risk of reintroduction. One way to reduce reintroduction risks is to eradicate the target invasive species from an entire archipelago, and thus eliminate readily available sources. We illustrate the costs and benefits of this approach with the efforts to remove invasive goats from the Galapagos Islands. Project Isabela, the world’s largest island restoration effort to date, removed >140,000 goats from >500,000 ha for a cost of US$10.5 million. Leveraging the capacity built during Project Isabela, and given that goat reintroductions have been common over the past decade, we implemented an archipelago-wide goat eradication strategy.
- Galápagos Monday: When Conservation Means Killing
- Galápagos Redux: When Is It OK to Kill Goats?
- Flynn’s proposal defense 11:30 – 1:30
- Qualitative study of mental models with respect to security?
- Limited qualitative studies in this area
- How do you transfer a sophisticated user to a more naive one?
- The profit model incentivised insecure design
- Biometric adoption (what about legal?)
- Experts are more disposed to use biometrics!
- Government guidance is broad, technical, and hard to use
- Commercial guidance is narrow and easier, but has a price
- What was the sampling technique?
- What does “technical” mean? Technospeak?
- What about a validation study to show that the approach works more than untrained small business users? What about confounding variables, like whether companies that participate are more likely to be security aware
- July 13-18 2020
- Centre Mont-Royal, Montrial, Quebec
- Call for papers (Due March 1, 2020)
- Complex dynamical systems and networks
- Artificial chemistry, origins of life, computational biology
- Synthetic biology, protocells and wet artificial life
- Ecology and evolution
- Bio-inspired, cognitive and evolutionary robotics, swarms
- Artificial intelligence and machine learning
- Perception, cognition, behavior
- Social systems, artificial and alternative societies
- Evolution of language, computational linguistics
- Philosophy of mind, philosophy of science
- Artificial-life-based art
- Artificial Life in education
- For this edition of the conference the special theme is “New Frontiers in AI: What can ALife offer AI?
AI and Compute
- We’re releasing an analysis showing that since 2012, the amount of compute used in the largest AI training runs has been increasing exponentially with a 3.4-month doubling time (by comparison, Moore’s Law had a 2-year doubling period).
Since 2012, this metric has grown by more than 300,000x (a 2-year doubling period would yield only a 7x increase). Improvements in compute have been a key component of AI progress, so as long as this trend continues, it’s worth preparing for the implications of systems far outside today’s capabilities
Does play matter? Functional and evolutionary aspects of animal and human play
- In this paper I suggest that play is a distinctive behavioural category whose adaptive significance calls for explanation. Play primarily affords juveniles practice toward the exercise of later skills. Its benefits exceed its costs when sufficient practice would otherwise be unlikely or unsafe, as is particularly true with physical skills and socially competitive ones. Manipulative play with objects is a byproduct of increased intelligence, specifically selected for only in a few advanced primates, notably the chimpanzee.
Dissertation – slooooooow going setting up the reflection and reflex section. Found some nice stuff on developing skills through training an play though
7:00 – 3:00 ASRC
3rd Annual DoD AI Industry Day
From Stewart Russell, via BBC Business Daily and the AI Alignment podcast:
Although people have argued that this creates a filter bubble or a little echo chamber where you only see stuff that you like and you don’t see anything outside of your comfort zone. That’s true. It might tend to cause your interests to become narrower, but actually that isn’t really what happened and that’s not what the algorithms are doing. The algorithms are not trying to show you the stuff you like. They’re trying to turn you into predictable clickers. They seem to have figured out that they can do that by gradually modifying your preferences and they can do that by feeding you material. That’s basically, if you think of a spectrum of preferences, it’s to one side or the other because they want to drive you to an extreme. At the extremes of the political spectrum or the ecological spectrum or whatever image you want to look at. You’re apparently a more predictable clicker and so they can monetize you more effectively.
So this is just a consequence of reinforcement learning algorithms that optimize click-through. And in retrospect, we now understand that optimizing click-through was a mistake. That was the wrong objective. But you know, it’s kind of too late and in fact it’s still going on and we can’t undo it. We can’t switch off these systems because there’s so tied in to our everyday lives and there’s so much economic incentive to keep them going.
So I want people in general to kind of understand what is the effect of operating these narrow optimizing systems that pursue these fixed and incorrect objectives. The effect of those on our world is already pretty big. Some people argue that operation’s pursuing the maximization of profit have the same property. They’re kind of like AI systems. They’re kind of super intelligent because they think over long time scales, they have massive information, resources and so on. They happen to have human components, but when you put a couple of hundred thousand humans together into one of these corporations, they kind of have this super intelligent understanding, manipulation capabilities and so on.
- Predicting human decisions with behavioral theories and machine learning
- Behavioral decision theories aim to explain human behavior. Can they help predict it? An open tournament for prediction of human choices in fundamental economic decision tasks is presented. The results suggest that integration of certain behavioral theories as features in machine learning systems provides the best predictions. Surprisingly, the most useful theories for prediction build on basic properties of human and animal learning and are very different from mainstream decision theories that focus on deviations from rational choice. Moreover, we find that theoretical features should be based not only on qualitative behavioral insights (e.g. loss aversion), but also on quantitative behavioral foresights generated by functional descriptive models (e.g. Prospect Theory). Our analysis prescribes a recipe for derivation of explainable, useful predictions of human decisions.
- Adversarial Policies: Attacking Deep Reinforcement Learning
- Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another agent’s observations. This might lead one to wonder: is it possible to attack an RL agent simply by choosing an adversarial policy acting in a multi-agent environment so as to create natural observations that are adversarial? We demonstrate the existence of adversarial policies in zero-sum games between simulated humanoid robots with proprioceptive observations, against state-of-the-art victims trained via self-play to be robust to opponents. The adversarial policies reliably win against the victims but generate seemingly random and uncoordinated behavior. We find that these policies are more successful in high-dimensional environments, and induce substantially different activations in the victim policy network than when the victim plays against a normal opponent. Videos are available at this http URL.
7:00 – 8:00 ASRC / Phd
The Journal of Design and Science (JoDS), a joint venture of the MIT Media Lab and the MIT Press, forges new connections between science and design, breaking down the barriers between traditional academic disciplines in the process.
There is a style of propaganda on the rise that isn’t interested in persuading you that something is true. Instead, it’s interested in persuading you that everything is untrue. Its goal is not to influence opinion, but to stratify power, manipulate relationships, and sow the seeds of uncertainty.
Unreal explores the first order effects recent attacks on reality have on political discourse, civics & participation, and its deeper effects on our individual and collective psyche. How does the use of media to design unreality change our trust in the reality we encounter? And, most important, how does cleaving reality into different camps—political, social or philosophical—impact our society and our future?
This looks really nice: The Illustrated GPT-2 (Visualizing Transformer Language Models)
Getting ready for a fun trip:
12th International Conference on Agents and Artificial Intelligence – Dammit, the papers are due October 4th. This would be a perfect venue for the GPT2 agents
Novelist Cormac McCarthy’s tips on how to write a great science paper
Unveiling the relation between herding and liquidity with trader lead-lag networks
- We propose a method to infer lead-lag networks of traders from the observation of their trade record as well as to reconstruct their state of supply and demand when they do not trade. The method relies on the Kinetic Ising model to describe how information propagates among traders, assigning a positive or negative “opinion” to all agents about whether the traded asset price will go up or down. This opinion is reflected by their trading behavior, but whenever the trader is not active in a given time window, a missing value will arise. Using a recently developed inference algorithm, we are able to reconstruct a lead-lag network and to estimate the unobserved opinions, giving a clearer picture about the state of supply and demand in the market at all times.
We apply our method to a dataset of clients of a major dealer in the Foreign Exchange market at the 5 minutes time scale. We identify leading players in the market and define a herding measure based on the observed and inferred opinions. We show the causal link between herding and liquidity in the inter-dealer market used by dealers to rebalance their inventories.
Continuing with the ICML 2019 Tutorial: Recent Advances in Population-Based Search for Deep Neural Networks. Wow. Lots of implications for diversity science. They need to read Martindale though.
This also looks good, using the above concepts of Quality Diversity to create map-like structures in low dimensions
- Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors
- Quality-Diversity optimization is a new family of optimization algorithms that, instead of searching for a single optimal solution to solving a task, searches for a large collection of solutions that all solve the task in a different way. This approach is particularly promising for learning behavioral repertoires in robotics, as such a diversity of behaviors enables robots to be more versatile and resilient. However, these algorithms require the user to manually define behavioral descriptors, which is used to determine whether two solutions are different or similar. The choice of a behavioral descriptor is crucial, as it completely changes the solution types that the algorithm derives. In this paper, we introduce a new method to automatically define this descriptor by combining Quality-Diversity algorithms with unsupervised dimensionality reduction algorithms. This approach enables robots to autonomously discover the range of their capabilities while interacting with their environment. The results from two experimental scenarios demonstrate that robot can autonomously discover a large range of possible behaviors, without any prior knowledge about their morphology and environment. Furthermore, these behaviors are deemed to be similar to handcrafted solutions that uses domain knowledge and significantly more diverse than when using existing unsupervised methods.
Back to the Dissertation
- Added notes from Monday’s dungeon run
- Added adversarial herding
- At 111 pages!