Author: <\/p>\n
Coming up with big ideas in technology used to take the kind of time and money that only large companies had.\u00a0 Now open source tools\u2014like TensorFlow<\/a>, which provides access to Google\u2019s machine learning technology\u2014mean anyone with a smart concept has the opportunity to make it a reality. Just ask Arjun Taneja and Vayun Mathur, two friends and high school students from Singapore with a big ambition to improve recycling rates.\u00a0\u00a0<\/p>\n Arjun and Vayun realized that separating waste is sometimes confusing and cumbersome\u2014something that can derail people’s good intentions<\/a> to recycle.\u00a0Using TensorFlow<\/a>, they built a \u201cSmart Bin\u201d that can identify types of trash and sort them automatically<\/a>. The Smart Bin uses a camera to take a picture of the object inserted in the tray, then analyzes the picture with a Convolutional Neural Network, a type of machine learning algorithm designed to recognize visual objects.\u00a0\u00a0<\/p>\n To train the algorithm, Arjun and Vayun took around 500 pictures of trash like glass bottles, plastic bottles, metal cans and paper. It\u2019s a process that would normally be laborious and expensive. But by using Google\u2019s Colab<\/a> platform for sharing resources and advice, the students could access a high powered graphics processor (GPU) in the cloud for free. They were also able to access Tensor Processing Units<\/a>, Google\u2019s machine learning processors which power services like Translate, Photos, Search, Assistant and Gmail. These tools helped their system analyze large amounts of data at once, so the students could correct the model if it didn’t recognize an object. As a result, the model learned to classify the objects even more quickly.\u00a0Once the Smart Bin was trained, all they had to do was place an object in the tray, and the system could predict whether it was metal, plastic, glass or paper\u2014with the answer popping up on a screen.\u00a0<\/p>\n Building on their successful trials at home, Arjun and Vayun showcased the Smart Bin with a stall at last week\u2019s Singapore Maker Faire<\/a>, and they continue to work on other projects. It\u2019s a great example of how tools available in the cloud are cutting out processes and costs that might have held back this kind of invention in the past.<\/p>\n<\/div>\n<\/div>\n<\/div>\n Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"