Goto

Collaborating Authors

* to NOW


Probabilistic Graphical Models

#artificialintelligence

Probabilistic graphical models (PGMs) are a rich framework for encoding probability distributions over complex domains: joint (multivariate) distributions over large numbers of random variables that interact with each other. These representations sit at the intersection of statistics and computer science, relying on concepts from probability theory, graph algorithms, machine learning, and more. They are the basis for the state-of-the-art methods in a wide variety of applications, such as medical diagnosis, image understanding, speech recognition, natural language processing, and many, many more. They are also a foundational tool in formulating many machine learning problems. This course is the first in a sequence of three.


Using machine learning to derive different causes from the same symptoms

#artificialintelligence

Machine learning is playing an ever-increasing role in biomedical research. Scientists at the Technical University of Munich (TUM) have now developed a new method of using molecular data to extract subtypes of illnesses. In the future, this method can help to support the study of larger patient groups. Nowadays doctors define and diagnose most diseases on the basis of symptoms. However, that does not necessarily mean that the illnesses of patients with similar symptoms will have identical causes or demonstrate the same molecular changes.


AI Is Like Lego; Why You Should Hire A Chief AI Now - AI Summary

#artificialintelligence

Artificial intelligence is no different to Lego; you want to make sure that different algorithms are compatible with each other, you want to make sure that the algorithms are correct and have minimal fault tolerance and when you start to combine different algorithms, you can create an algorithmic business with enormous potential. And to manage this AI Lego building process, your organisation requires a Chief AI. Since the Chief AI has a clear understanding of the business objectives of the organisation as well as the available technology already in-house, the Chief AI should be able to attract the right AI talent. Next to attracting the right AI talent, the Chief AI should be able to retain this talent by offering them interesting and challenging AI projects. Therefore, the Chief AI should be able to understand the business needs and be able to translate these to technical requirements and adapt (existing) AI tools to the business needs.


Research Papers based on Gated RNN'S(Deep Learning)

#artificialintelligence

Abstract: Data augmentation has proven to be a promising prospect in improving the performance of deep learning models by adding variability to training data. In previous work with developing a noise robust acoustic-to-articulatory speech inversion system, we have shown the importance of noise augmentation to improve the performance of speech inversion in noisy speech. In this work, we compare and contrast different ways of doing data augmentation and show how this technique improves the performance of articulatory speech inversion not only on noisy speech, but also on clean speech data. We also propose a Bidirectional Gated Recurrent Neural Network as the speech inversion system instead of the previously used feed forward neural network. The inversion system uses mel-frequency cepstral coefficients (MFCCs) as the input acoustic features and six vocal tract-variables (TVs) as the output articulatory features.


Research Papers about the developments in the Finite State Automation

#artificialintelligence

Abstract: Graph-based neural network models are producing strong results in a number of domains, in part because graphs provide flexibility to encode domain knowledge in the form of relational structure (edges) between nodes in the graph. In practice, edges are used both to represent intrinsic structure (e.g., abstract syntax trees of programs) and more abstract relations that aid reasoning for a downstream task (e.g., results of relevant program analyses). In this work, we study the problem of learning to derive abstract relations from the intrinsic graph structure. Motivated by their power in program analyses, we consider relations defined by paths on the base graph accepted by a finite-state automaton. We show how to learn these relations end-to-end by relaxing the problem into learning finite-state automata policies on a graph-based POMDP and then training these policies using implicit differentiation.


Robots that act collectively: when, and how? – #ICRA2022 Day 4 interview with K. Petersen, M. A. Olivares Mendez, and T. Kaiser ( video digest)

Robohub

Attending ICRA is a great opportunity to see many state-of-the-art (and famous?) robots in a single venue. Indeed, a quick trip to the exhibitors' booths is enough to get introduced to the large and diverse group of commercial robots we have today. Yet, one can easily notice that these amazing state-of-the-art robots do not interact with each other. At least they do not do it without human mediation. Although in the exhibitions one can find two or three robots that appear to be joyfully playing together, the reality is that their operators are creating these inter-robot interactions.


How Can AI Chatbots Help Improve Customer Experience

#artificialintelligence

Chatbots are increasingly being used by businesses for numerous business applications, especially customer service. The main reason behind this is that they can help improve your customer experiences. One of the main reasons why people love to interact with chatbots for customer support is that they don†t have to wait to talk to a human agent. In today†s age, consumers have become very demanding and they want instant responses. To meet this demand, businesses might have to hire more people to work in different shifts and provide 24 7 support.


Artificial Neural Network Encoding of Molecular Wavefunction for Quantum Computing

#artificialintelligence

Artificial neural networks (ANNs) for material modeling have received significant interest. We recently reported an adaptation of ANNs based on Boltzmann machine (BM) architectures to an ansatz of the multiconfigurational many-electron wavefunction, designated neural-network quantum state (NQS), for quantum chemistry calculations. Here, this study presents its extended formalism to a quantum algorithm that enables the preparation of the NQS through quantum gates. The descriptors of the ANN model, which are chosen as occupancies of electronic configurations, are quantum-mechanically represented by qubits. Our algorithm may thus bring potential advantages over classical sampling-based computation employed in the previous studies.


Brain Tumor Detection using Machine Learning, Python, and GridDB

#artificialintelligence

Brain tumors are one of the most challenging diseases for clinical researchers, as it causes severe harm to patients. The brain is a central organ in the human body, and minor damage to this organ could affect the correct functioning of the human body. Brain tumors can lead to irreversible and dysfunctional damage to patients, including memory and vision loss. For these reasons, medical studies have, for a long time, focused on the study of the brain and its diseases, including brain tumors. Computer studies have contributed to medical research by offering machine learning algorithms to classify medical analysis records as brain tumors or normal clinical conditions.


Urban Rhapsody: Large-scale exploration of urban soundscapes

#artificialintelligence

Noise is one of the primary quality-of-life issues in urban environments. While low-cost sensors can be deployed to monitor ambient noise levels at high temporal resolutions, the amount of data they produce and the complexity of these data pose significant analytical challenges. One way to address these challenges is through machine listening techniques, which are used to extract features in attempts to classify the source of noise and understand temporal patterns of a city's noise situation. However, the overwhelming number of noise sources in the urban environment and the scarcity of labeled data makes it nearly impossible to create classification models with large enough vocabularies that capture the true dynamism of urban soundscapes In this paper, we first identify a set of requirements in the yet unexplored domain of urban soundscape exploration. To satisfy the requirements and tackle the identified challenges, we propose Urban Rhapsody, a framework that combines state-of-the-art audio representation, machine learning, and visual analytics to allow users to interactively create classification models, understand noise patterns of a city, and quickly retrieve and label audio excerpts in order to create a large high-precision annotated database of urban sound recordings.