BEGIN:VCALENDAR VERSION:2.0 PRODID:-//KnowAFest//Campus Events//EN BEGIN:VEVENT UID:eventsphere-52809@www.knowafest.com DTSTAMP:20261008T162421Z DTSTART:20180906T183000Z DTEND:20180907T182959Z SUMMARY:One day hands on workshop BIO MIMICRY AND MACHINE LEARNING using py thon 2018 LOCATION:Coimbatore Institute of Technology\, Coimbatore DESCRIPTION:

Bio Mimicry and Communication:-
\n
\nKnowledge tra nsfer across domains leads to significant breakthroughs in science and tec hnology.
\nFor example\, through biomimicry\, innovators get inspirat ion from nature/biology to solve complex engineering problems.
\n
\nAn exciting example of biomimicry is the recent creation of artificial materials that imitate the surface of cicada’s wings and gecko’s skin \, which have antibacterial properties due to their physical structure. Th ese type of materials could be used in hospitals for surfaces that get eas ily contaminated with bacteria and help drastically reduce the number of h ospital infections\, a leading cause of health complications during hospit alization.
\nBiomimicry inventions and discoveries are usually highly creative and efficient. However\, they happen due to serendipity: knowled ge transfer between biology and engineering is not straightforward since b oth are studied in isolation of each other. There are no systematic ways t o incorporate ideas from nature/biology into the design process of enginee ring solutions.
\nA knowledge base of biology goals and mechanisms an d an “intelligent” tool to navigate and map them to engineering proble ms would take serendipity out of the loop and provide a systematic way of connecting engineering challenges to biology inspiration.
\n
\nM achine learning is an application of artificial intelligence (AI) that pro vides systems the ability to automatically learn and improve from experien ce without being explicitly programmed. Machine learning focuses on the de velopment of computer programs that can access data and use it learn for t hemselves.
\n
\nThe process of learning begins with observations or data\, such as examples\, direct experience\, or instruction\, in orde r to look for patterns in data and make better decisions in the future bas ed on the examples that we provide. The primary aim is to allow the comput ers learn automatically without human intervention or assistance and adjus t actions accordingly.
\n
\nMachine learning:-
\n
\nMa chine learning algorithms are often categorized as supervised or unsupervi sed.
\nSupervised machine learning algorithms can apply what has been learned in the past to new data using labeled examples to predict future events. Starting from the analysis of a known training dataset\, the learn ing algorithm produces an inferred function to make predictions about the output values. The system is able to provide targets for any new input aft er sufficient training. The learning algorithm can also compare its output with the correct\, intended output and find errors in order to modify the model accordingly.In contrast\, unsupervised machine learning algorithms are used when the information used to train is neither classified nor labe led. Unsupervised learning studies how systems can infer a function to des cribe a hidden structure from unlabeled data. The system doesn’t figure out the right output\, but it explores the data and can draw inferences fr om datasets to describe hidden structures from unlabeled data.Semi-supervi sed machine learning algorithms fall somewhere in between supervised and u nsupervised learning\, since they use both labeled and unlabeled data for training – typically a small amount of labeled data and a large amount o f unlabeled data. The systems that use this method are able to considerabl y improve learning accuracy. Usually\, semi-supervised learning is chosen when the acquired labeled data requires skilled and relevant resources in order to train it / learn from it. Otherwise\, acquiringunlabeled data gen erally doesn’t require additional resources.Reinforcement machine learni ng algorithms is a learning method that interacts with its environment by producing actions and discovers errors or rewards. Trial and error search and delayed reward are the most relevant characteristics of reinforcement learning. This method allows machines and software agents to automatically determine the ideal behavior within a specific context in order to maximi ze its performance. Simple reward feedback is required for the agent to le arn which action is best\; this is known as the reinforcement signal.
\n
\nMachine learning enables analysis of massive quantities of data . While it generally delivers faster\, more accurate results in order to i dentify profitable opportunities or dangerous risks\, it may also require additional time and resources to train it properly. Combining machine lear ning with AI and cognitive technologies can make it even more effective in processing large volumes of information.

URL:https://www.knowafest.com/one-day-hands-on-workshop-bio-mimicry-and-mac hine-learning-using-python-2018 END:VEVENT END:VCALENDAR