Learn to build decision trees for applied machine learning from scratch in Python. Decision trees are one of the hottest topics in Machine Learning. They dominate many Kaggle competitions nowadays. This course covers both fundamentals of decision tree algorithms such as CHAID, ID3, C4.5, CART, Regression Trees and its hands-on practical applications. Besides, we will mention some bagging and boosting methods such as Random Forest or Gradient Boosting to increase decision tree accuracy.

Amazon's 2019 Climate Pledge calls for a commitment to net zero carbon across their businesses by 2040. Since then, the company has reduced the weight of their outbound packaging by 33%, eliminating 915,000 tons of packaging material worldwide, or the equivalent of over 1.5 billion shipping boxes. With less packaging used throughout the supply chain, volume per shipment is reduced and transportation becomes more efficient. The cumulative impact across Amazon's enormous network is a dramatic reduction in carbon emissions. To make this happen, the customer packaging experience team partnered with AWS to build a machine learning solution powered by Amazon SageMaker.

I have done an introduction to Artificial Intelligence (AI) course and I want to share my learning experience. This post covers my notes and summaries of the content of the course. On the early sixties, there was a gathering between several investigators interested on artificial intelligence, neural networks and automats theory as a consequence of the first works made on the field. The problem resolution was based on a general purpose search engine with high cost. To lower that cost, the first search algorithms were developed, like Heuristic Search and Alpha Beta Search.

AI and Machine Learning Demystified by Carol Smith at Midwest UX 2017 from Carol Smith Hoy traemos a este espacio esta slideshare titulada "AI and Machine Learning Demystified by Carol " que nos presentan así What is machine learning? Is UX relevant in the age of artificial intelligence (AI)? How can I take advantage of cognitive computing? Get answers to these questions and learn about the implications for your work in this session. Carol will help you understand at a basic level how these systems are built and what is required to get insights from them.

Artificial intelligence is having a growing impact on our daily lives and is also revolutionizing research. ETH Zurich recognizes its responsibility in this area and is striving to promote innovation and trust in this fast-evolving technology. Sometimes a machine takes everyone by surprise. A recent example occurred at the opening event of Scientifica 2019, where ETH robotics specialists had trained a drone to welcome visitors by writing the word "enjoy." At first everything seemed normal as the drone, known as Voliro, began to write.

This paper surveys the field of transfer learning in the problem setting of Reinforcement Learning (RL). RL has been the key solution to sequential decision-making problems. Along with the fast advance of RL in various domains. including robotics and game-playing, transfer learning arises as an important technique to assist RL by leveraging and transferring external expertise to boost the learning process. In this survey, we review the central issues of transfer learning in the RL domain, providing a systematic categorization of its state-of-the-art techniques. We analyze their goals, methodologies, applications, and the RL frameworks under which these transfer learning techniques would be approachable. We discuss the relationship between transfer learning and other relevant topics from an RL perspective and also explore the potential challenges as well as future development directions for transfer learning in RL.

We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database schemas). GAZP combines a forward semantic parser with a backward utterance generator to synthesize data (e.g. utterances and SQL queries) in the new environment, then selects cycle-consistent examples to adapt the parser. Unlike data-augmentation, which typically synthesizes unverified examples in the training environment, GAZP synthesizes examples in the new environment whose input-output consistency are verified. On the Spider, Sparc, and CoSQL zero-shot semantic parsing tasks, GAZP improves logical form and execution accuracy of the baseline parser. Our analyses show that GAZP outperforms data-augmentation in the training environment, performance increases with the amount of GAZP-synthesized data, and cycle-consistency is central to successful adaptation.

Advances in deep learning have enabled the development of models that have exhibited a remarkable tendency to recognize and even localize actions in videos. However, they tend to experience errors when faced with scenes or examples beyond their initial training environment. Hence, they fail to adapt to new domains without significant retraining with large amounts of annotated data. Current algorithms are trained in an inductive learning environment where they use data-driven models to learn associations between input observations with a fixed set of known classes. In this paper, we propose to overcome these limitations by moving to an open world setting by decoupling the ideas of recognition and reasoning. Building upon the compositional representation offered by Grenander's Pattern Theory formalism, we show that attention and commonsense knowledge can be used to enable the self-supervised discovery of novel actions in egocentric videos in an open-world setting, a considerably more difficult task than zero-shot learning and (un)supervised domain adaptation tasks where target domain data (both labeled and unlabeled) are available during training. We show that our approach can be used to infer and learn novel classes for open vocabulary classification in egocentric videos and novel object detection with zero supervision. Extensive experiments show that it performs competitively with fully supervised baselines on publicly available datasets under open-world conditions. This is one of the first works to address the problem of open-world action recognition in egocentric videos with zero human supervision to the best of our knowledge.

Joint entity and relation extraction aims to extract relation triplets from plain text directly. Prior work leverages Sequence-to-Sequence (Seq2Seq) models for triplet sequence generation. However, Seq2Seq enforces an unnecessary order on the unordered triplets and involves a large decoding length associated with error accumulation. These introduce exposure bias, which may cause the models overfit to the frequent label combination, thus deteriorating the generalization. We propose a novel Sequence-to-Unordered-Multi-Tree (Seq2UMTree) model to minimize the effects of exposure bias by limiting the decoding length to three within a triplet and removing the order among triplets. We evaluate our model on two datasets, DuIE and NYT, and systematically study how exposure bias alters the performance of Seq2Seq models. Experiments show that the state-of-the-art Seq2Seq model overfits to both datasets while Seq2UMTree shows significantly better generalization. Our code is available at https://github.com/WindChimeRan/OpenJERE .

Competitions play an invaluable role in the field of forecasting, as exemplified through the recent M4 competition. The competition received attention from both academics and practitioners and sparked discussions around the representativeness of the data for business forecasting. Several competitions featuring real-life business forecasting tasks on the Kaggle platform has, however, been largely ignored by the academic community. We believe the learnings from these competitions have much to offer to the forecasting community and provide a review of the results from six Kaggle competitions. We find that most of the Kaggle datasets are characterized by higher intermittence and entropy than the M-competitions and that global ensemble models tend to outperform local single models. Furthermore, we find the strong performance of gradient boosted decision trees, increasing success of neural networks for forecasting, and a variety of techniques for adapting machine learning models to the forecasting task.