Intelligent Automation for Work and Life
At Quantilus, we have been working with AI before it became cool (and scary). Our first foray was in the field of Natural Language Processing – which we used for automated grammar and style checks of written content. Subsequently, we built tools to classify untagged content in intelligent, usable ways, and to present it for consumption with a high degree of personalization. More recently, we have been working on personality assessment of individuals based on 1) the words they speak (a relatively simple task), and 2) changes in their facial patterns based on verbal and visual cues (a much more complex task).
Want to build Virtual Reality or Augmented Reality apps for your business? We built some of the first business-focused AR apps for mobile and wearable platforms through our SAP partnership. Our apps help technical support personnel visualize product models, and also let customers visualize retail products in empty space. With the added complexity of tight integration with backend ERP systems.
FEATURED WORK
TECHNOLOGY STACK
Some of the frameworks and tools that our development teams have used recently. A list that grows by the day.
RELATED RESEARCH
Relevant, interesting and current curated research content in the field.
Detecting Offensive Language in Tweets Using Deep Learning
This paper addresses the important problem of discerning hateful content in social media. It proposes a detection scheme that is an ensemble of Recurrent Neural Network (RNN) classifiers, and it incorporates various features associated with user-related information, such as the users’ tendency towards racism or sexism. These data are fed as input to the above classifiers along with the word frequency vectors derived from the textual content. The scheme can successfully distinguish racist and sexist messages from normal text, and achieve higher classification quality than current state-of-the-art algorithms.
Distributed Deep Reinforcement Learning: learn how to play Atari games in 21 minutes
This paper presents a study in Distributed Deep Reinforcement Learning (DDRL) focused on scalability of a state-of-the-art Deep Reinforcement Learning algorithm known as Batch Asynchronous Advantage ActorCritic (BA3C). Using synchronous training on the node level (while keeping the local, single node part of the algorithm asynchronous) and minimizing the memory footprint of the model, allowed the authors to achieve linear scaling for up to 64 CPU nodes. This corresponds to a training time of 21 minutes on 768 CPU cores, as opposed to 10 hours when using a single node with 24 cores achieved by a baseline single-node implementation.
Collective Intelligence
As examples like Wikipedia, Google, and Linux illustrate, new information and communication technologies are now enabling dramatically new ways of connecting large numbers of people and computers to produce intelligent behavior. These new forms of “collective intelligence” are already having significant economic, social, and political effects, and their effects are likely to be even more transformational in the coming decades. Understanding these possibilities is one of the most important challenges—and opportunities—facing the social, behavioral, and economic sciences today.
Conversational AI: The Science Behind the Alexa Prize
Much work remains in the area of social conversation as well as free-form conversation over a broad range of domains and topics. To advance the state of the art in conversational AI, Amazon launched the Alexa Prize, a 2.5-million-dollar university competition where sixteen selected university teams were challenged to build conversational agents, known as “socialbots”, to converse coherently and engagingly with humans on popular topics such as Sports, Politics, Entertainment, Fashion and Technology for 20 minutes. This paper outlines the advances created by the university teams as well as the Alexa Prize team to achieve the common goal of solving the problem of Conversational AI.