Researchers at Carnegie Mellon University and Pennsylvania State University, USA have developed trained AI agents that are are able to adopt human design strategies for creative and exploratory decision making, using neural networks. The study was co-authored by Jonathan Cagan, professor of mechanical engineering and Ayush Raina, a PhD candidate along with Chris McComb, an assistant professor of engineering design. The findings were published in the reputed ASME Journal of Mechanical Design.
Crux of the Matter
Is AI an Army of Robots Out to Kill Us? AI or Artificial Intelligence is giving the abilities to a machine for performing a task that reduces human effort. According to the father of AI, John McCarthy, it is “The science and engineering of making intelligent machines, especially intelligent computer programs”. AI is dominant in fields like Gaming, Expert Systems, Vision Systems, Natural Language Processing (NLP) and Speech Recognition.
What was This Study About? When engineers use AI, they simply apply it to a problem within a defined set of rules rather than having it generally follow human strategies to create something new. The framework in this study was made up of multiple deep neural networks that worked together in a prediction-based situation by looking through a set of five sequential images and estimating the output of the next design. Then an AI framework learns human design strategies through observation of human data to generate new designs without explicit goal information, bias, or guidance. Visualization was thereby emphasized in the process because vision is an integral part of how humans perceive the world and go about solving problems.
So How Good can this AI be? According to Cagan, quite good as he says, “The AI is not just mimicking or regurgitating solutions that already exist. It’s learning how people solve a specific type of problem and creating new design solutions from scratch.” In times ahead, they would have to tackle truss problems and derive new strategies for it. Commonly seen in bridges, a truss is an assembly of rods forming a complete structure and their problems represent complex engineering design challenges.
Watch this #robot conduct a human orchestra By @nowthisnews RT @Fabriziobustama#AI #ArtificialIntelligence #Robotics #tech #innovation #IoT #MachineLearning Cc: @Nicochan33 @mvollmer1 @FrRonconi @sebbourguignon @ka… pic.twitter.com/MULsvGtc4i — DigitalKE (@digitalked) March 7, 2020
Curiopedia
A neural network – is a series of algorithms that endeavors to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates. In this sense, neural networks refer to systems of neurons, either organic or artificial in nature. They can also adapt to changing input, in order to make the network generates the best possible result without needing to redesign the output criteria. This network works similarly to the human brain’s neural network contains layers of interconnected nodes. A “neuron” in a neural network is a mathematical function that collects and classifies information according to a specific architecture. The network bears a strong resemblance to statistical methods such as curve fitting and regression analysis. More Info
Curated Coverage
Comentarios