For some technical backbone to this piece,see here. Also 1) Turns out IQ beats random selection in the best of applications by less than 6%, typically 2%, as the computation of correlations have a flaw and psychologists do not seem to know the informational value of correlation in terms of "how much do I gain information about B knowing A" and propagation of error (intra-test variance for a single individual). The psychologists who engaged me on this piece -- with verbose writeups --made the mistake of showing me the best they got: papers with the strongest pro-IQ arguments. They do not seem to grasp what noise/signal really means in practice. Background: "IQ" is a stale test meant to measure mental capacity but in fact mostly measures extreme unintelligence (learning difficulties), as well as, to a lesser extent (with a lot of noise), a form of intelligence, stripped of 2nd order effects -- how good someone is at taking some type of exams designed by unsophisticated nerds.

Zygmunt received his PhD degree in Computer Science from the University of Adelaide, Australia in 2013, and his MSc degree in Computer Science from the University of KwaZulu-Natal, South Africa in 2009. He is a senior research fellow at the Australian Institute for Machine Learning. His research lies at the interface of computer vision, machine learning, and challenging industry problems. He develops algorithms that allow computers to perform tasks typically associated with human intelligence. In the last couple of years, his work has focused on the application of machine learning and image processing techniques for the development of smart medical devices.

It feels impossible to keep up with every new concept and technology in data science and machine learning. You have multiple languages, libraries and design principles. We have written pieces on different resources that can help data professionals keep up to date with all the various technologies. However, many of these courses cost money. But coursera offers an opportunity to take online courses for free from actual colleges and educational institutions.

Recent surveys, studies, forecasts and other quantitative assessments of the impact and progress of AI highlighted the need to retrain many workers, improving AI's score from F to A on 8th-grade science exam, and the $97.9 billion the AI market will reach in 2023. In the next three years, as many as 120 million workers in the world's 12 largest economies may need to be retrained or reskilled as a result of AI and intelligent automation; only 41% of CEOs surveyed say that they have the people, skills and resources required to execute their business strategies; the time it takes to close a skills gap through training has increased from 3 days on average in 2014 to 36 days in 2018 [IBM] Top drivers for investing in robotics and automation: Reduced cost (80%), improved quality (55%), increased productivity (54%), improved capabilities of robots (54%). L'Oréal's recruiters believe they saved 200 hours of time to hire 80 interns out of a pool of 12,000 candidates, using a chatbot that saves significant time in the early stages of the recruiting process by handling questions from candidates, and Seedlink, AI software that assesses their responses to open-ended interview questions [Forbes]

One of the main obstacles for developing flexible AI system is the split between data-based learners and model-based solvers. Solvers such as classical planners are very flexible and can deal with a variety of problem instances and goals but require first-order symbolic models. Data-based learners, on the other hand, are robust but do not produce such representations. In this work we address this split by showing how the first-order symbolic representations that are used by planners can be learned from non-symbolic representations alone given by a number of observed system trajectories organized as graphs. The observations can be arbitrary, including raw images. What it is required is that two observations are different iff they proceed from different states. The representation learning problem is formulated as the problem of inferring the simplest planning instances over a common first-order domain that can generate the structures of the observed graphs. A slightly richer version of the problem is also considered where actions are also observed and the graphs are labeled. The problem is expressed and solved via a SAT formulation that is shown to produce first-order representations for domains like Gripper, Blocks, and Hanoi. The work suggests that the target symbolic representations for planning encode the structure of the observed state space, not the observations themselves, as assumed in deep learning approaches.

Machine education is an emerging research field that focuses on the problem which is inverse to machine learning. To date, the literature on educating machines is still in its infancy. A fairly low number of methodology and method papers are scattered throughout various formal and informal publication avenues, mainly because the field is not yet well coalesced (with no well established discussion forums or investigation pathways), but also due to the breadth of its potential ramifications and research directions. In this study we bring together the existing literature and organise the discussion into a small number of research directions (out of many) which are to date sufficiently explored to form a minimal critical mass that can push the machine education concept further towards a standalone research field status.

We plot the judge's probability of the target answer given that sentence against how often humans also select that target answer given that same sentence. Humans tend to find a sentence to be strong evidence for an answer when the judge model finds it to be strong evidence. Strong evidence to a model tends to be strong evidence to humans as shown in Figure 7. Combined with the previous result, we can see that learned agents are more accurate at predicting sentences that humans find to be strong evidence. F Model Evaluation of Evidence on DREAM Figure 8 shows how convincing various judge models find each evidence agent. Our findings on DREAM are similar to those from RACE in §4.2. Figure 8: On DREAM, how often each judge selects an agent's answer when given a single agent-chosen sentence. The black line divides learned agents (right) and search agents (left), with human evidence selection in the leftmost column. All agents find evidence that convinces judge models more often than a no-evidence baseline (33%). Learned agents predicting p ( i) or p ( i) find the most broadly convincing evidence.

The exploration mechanism used by a Deep Reinforcement Learning (RL) agent plays a key role in determining its sample efficiency. Thus, improving over random exploration is crucial to solve long-horizon tasks with sparse rewards. We propose to leverage an ensemble of partial solutions as teachers that guide the agent's exploration with action suggestions throughout training. While the setup of learning with teachers has been previously studied, our proposed approach - Actor-Critic with Teacher Ensembles (AC-Teach) - is the first to work with an ensemble of suboptimal teachers that may solve only part of the problem or contradict other each other, forming a unified algorithmic solution that is compatible with a broad range of teacher ensembles. AC-Teach leverages a probabilistic representation of the expected outcome of the teachers' and student's actions to direct exploration, reduce dithering, and adapt to the dynamically changing quality of the learner. We evaluate a variant of AC-Teach that guides the learning of a Bayesian DDPG agent on three tasks - path following, robotic pick and place, and robotic cube sweeping using a hook - and show that it improves largely on sampling efficiency over a set of baselines, both for our target scenario of unconstrained suboptimal teachers and for easier setups with optimal or single teachers. Additional results and videos at https://sites.google.com/view/acteach/home.

Question answering has seen significant advances in recent times, especially with the introduction of increasingly bigger transformer-based models pre-trained on massive amounts of data. While achieving impressive results on many benchmarks, their performances appear to be proportional to the amount of training data available in the target domain. In this work, we explore the ability of current question-answering models to generalize - to both other domains as well as with restricted training data. We find that large amounts of training data are necessary, both for pre-training as well as fine-tuning to a task, for the models to perform well on the designated task. We introduce a novel abductive reasoning approach based on Grenander's Pattern Theory framework to provide self-supervised domain adaptation cues or "pseudo-labels," which can be used instead of expensive human annotations. The proposed self-supervised training regimen allows for effective domain adaptation without losing performance compared to fully supervised baselines. Extensive experiments on two publicly available benchmarks show the efficacy of the proposed approach. We show that neural networks models trained using self-labeled data can retain up to $75\%$ of the performance of models trained on large amounts of human-annotated training data.

Multi-agent reinforcement learning has shown promise on a variety of cooperative tasks as a consequence of recent developments in differentiable inter-agent communication. However, most architectures are limited to pools of homogeneous agents, limiting their applicability. Here we propose a modular framework for learning complex tasks in which a traditional monolithic agent is framed as a collection of cooperating heterogeneous agents. We apply this approach to model sensorimotor coordination in the neocortex as a multi-agent reinforcement learning problem. Our results demonstrate proof-of-concept of the proposed architecture and open new avenues for learning complex tasks and for understanding functional localization in the brain and future intelligent systems.