In this competition, you're challenged to build a model that recognizes toxicity and minimizes this type of unintended bias with respect to mentions of identities. You'll be using a dataset labeled for identity mentions and optimizing a metric designed to measure unintended bias. Develop strategies to reduce unintended bias in machine learning models, and you'll help the Conversation AI team, and the entire industry, build models that work well for a wide range of conversations.
In these challenges your task is to process In-phase/Quadrature voltages (known as I/Q signals, see the References section at the end of this document for more information) measured by a broadband HF antenna that is connected to a set of Software Defined Radios (SDR). The SDRs were time-synchronized with Global Positioning System (GPS) timing. All PINS I/Q recordings were made at several locations in the United States. Within these recordings are many unique signals with a wide variety of modulations and signal strengths, and the recorded signals propagated between sites by ground wave and/or skywave.
In the challenge, participants will be tasked with predicting which accommodations (items) have been clicked in the search result during the last part of a user session in an offline evaluation setup. To this end, trivago will release a public dataset of hotel search sessions.
Context-aware multi-modal transportation recommendation has a goal of recommending a travel plan which considers various unimodal transportation modes, such as walking, cycling, driving, public transit, and how to connect among these modes under various contexts. The successful development of multi-modal transportation recommendations can have a number of advantages, including but not limited to reducing transport times, balancing traffic flows, reducing traffic congestion, and ultimately, promoting the development of intelligent transportation systems.
Actian has just released the cloud data warehouse managed service in AWS. Actian Avalanche can provide up to 20-times the performance at a third of the cost of alternative offerings at an enterprise-class scale with superior concurrency. We would like to build a demo application that showcases the performance, resiliency and the concurrency advantage of our service, compared to the other cloud data warehouses that exist in AWS. We would like this challenge to showcase these advantages by building an application with a data science and analytics-oriented use case.
Single-cell -omics Trajectory Inference (TI) methods are essential tools for the analysis of cellular dynamic process and to understand gene regulation. More than 60 methods have been developed and the list still keeps growing. It's time to bring fresh ideas to this emerging and exciting field and keep improving.
One form of biometric authentication is voice recognition, which makes it possible to identify a person. Often voice verification algorithms are trying to fool intruders. You are invited to create an algorithm that can distinguish the human voice (human) from the spoofed speech (spoof).
By analyzing news data to predict stock prices, Kagglers have a unique opportunity to advance the state of research in understanding the predictive power of the news. This power, if harnessed, could help predict financial outcomes and generate significant economic impact all over the world.
Through this KDD Cup|Humanity RL track competition we are looking for participants to apply machine learning tools to determine novel solutions which could impact malaria policy in Sub Saharan Africa. Specifically, how should combinations of interventions which control the transmission, prevalence and health outcomes of malaria infection, be distributed in a simulated human population.
In this competition, you will develop an algorithm that can predict the magnetic interaction between two atoms in a molecule (i.e., the scalar coupling constant).
Once the competition finishes, CHAMPS would like to invite the top teams to present their work, discuss the details of their models, and work with them to write a joint research publication which discusses an open-source implementation of the solution.
The NL2SQL Challenge, using financial and general domain tabular data as the data source, provides pairs of natural language question and SQL statement annotated based on the tabular data. Contestants can use the annotated data to develop methods that can accurately convert natural language question to corresponding SQL.
The objective of this competition is to create a machine learning model to detect fraudulent transactions.
Fraud detection is an important application of machine learning in the financial services sector. This solution will help Xente provide improved and safer service to its customers.
The objective of the new ChaLearn AutoDL challenge series, organized with Google and 4Paradigm, is to address some of the limitations of the previous challenges and provide an ambitious benchmark multi-class classification problems without any human intervention, in limited time, on any large-scale dataset composed of samples either in tabular format, 2d matrices, time series, or spatio-temporal series. Data are formatted in a uniform way as 4d tensors (t, x, y, channel). This lends itself in particular to the use of convolutional neural networks (CNNs). Although the use of TensorFlow is facilitated by providing participants with a starting kit including sample code demonstrating how to solve the problems at hand with TensorFlow, the participants are free to provide solutions not using TensorFlow.
In this track of the Challenge, you are asked to detect pairs of objects and the relationships that connect them.
The training set contains 329 relationship triplets with 375k training samples. These include both human-object relationships (e.g. "woman playing guitar", "man holding microphone"), object-object relationships (e.g. "beer on table", "dog inside car"), and also considers object-attribute relationships (e.g."handbag is made of leather" and "bench is wooden").
In this track of the Challenge, you are asked to predict a tight bounding box around object instances.
The training set contains 12.2M bounding-boxes across 500 categories on 1.7M images. The boxes have been largely manually drawn by professional annotators to ensure accuracy and consistency. The images are very diverse and often contain complex scenes with several objects (7 per image on average).