BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Montreal BEGIN:DAYLIGHT DTSTART:20210314T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20201101T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20210308T161016Z UID:66EC0F7A-2098-491F-B6CC-8F3D82121137 DTSTART;TZID=America/Montreal:20201106T120000 DTEND;TZID=America/Montreal:20201106T130000 DESCRIPTION:When and How\n\nDate: November 6th\, 2020\n\nTime: 12:00 pm – 1:00 pm Eastern Time\n\nLocation: Saint Maurice\, Trois Rivieres\, Quebec \n\nZOOM : https://uqtr.zoom.us/j/89805026456?pwd=bzluWlp0elY3clJzY0szYXpy a2pZdz09\n\nMeeting ID: 898 0502 6456 Password: 237973\n\nABSTRACT\n\nMach ine learning and deep learning tools have been rapidly advancing in capabi lities over the past 7 years – they have transformed the fields of compu ter vision\, speech\, natural language processing\, and control systems in complex environments by scaling to systems which can learn from massive s ets of real-world data and feedback. More recently\, in the past 4 years\, radio signal processing and communications systems have been beginning to undergo this same transformation – from relatively compact analytic sys tem and world models to rich data-driven representations of signals\, impa irments\, channel phenomenon\, and otherwise. Recent IEEE initiative such as the IEEE Machine Learning for Communications (MLC) Emerging Technology Area (ETI) have focused on highlighting and adapting ComSoc to some of the se new challenging and embracing this approach for a number of problems.\n \nOur work at DeepSig and Virginia Tech has focused heavily on transitioni ng data-driven baseband radio processing techniques for communications sys tems in point-to-point\, mesh\, 5G\, and 6G systems to data-driven end-to- end learned models\, and leveraging data-driven deep learning models for r eal-time sensing and sense-making of radio spectrum activity – consuming high rates of raw sensor data and turning it into useful analytics\, mapp ing\, anomaly detection\, and real time information to enable scheduling a nd reactivity in the radio access network.\n\nThis talk will highlight key enablers which the communications society has begun to embrace\, will dis cuss the trade-offs and pros and cons of model driven\, data-driven\, and joint model/data-driven methods for signal processing. We will highlight a number of key works in this area\, highlighting where data-driven methods in communications are highly effective\, and some areas where et hey are not. We will give a deep dive on how we are applying data-driven communica tions systems to several immediate and pertinent industry applications\, s peculate about where things are going\, and how the fields of communicatio ns\, signal processing\, information theory\, and machine learning will co ntinue to co-evolve and lead to exciting new opportunities and research.\n \nBy Dr. Tim O’Shea\, Co-Founder/CTO of DeepSig\n\nSpeaker(s): Tim O'She a\, \n\n3351 Boulevard des Forges\, \, Trois Rivieres\, Quebec\, Canada\, G9A 5H7\, Virtual: https://events.vtools.ieee.org/m/244449 LOCATION:3351 Boulevard des Forges\, \, Trois Rivieres\, Quebec\, Canada\, G9A 5H7\, Virtual: https://events.vtools.ieee.org/m/244449 ORGANIZER:messaoud.ahmed.ouameur@uqtr.ca SEQUENCE:7 SUMMARY:EMBRACING DATA-DRIVEN SIGNAL PROCESSING IN COMMUNICATIONS SYSTEMS: END-TO-END LEARNING FOR COMMUNICATIONS SYSTEMS ALGORITHMS TO EXCEL IN THE REAL WORLD URL;VALUE=URI:https://events.vtools.ieee.org/m/244449 X-ALT-DESC:Description: <br /><p><strong><span style="background-color: #00 ccff\;">When and How</span></strong></p>\n<p><strong>&nbsp\;&nbsp\; Date:< /strong> &nbsp\; November 6th\, 2020</p>\n<p><strong>&nbsp\;&nbsp\; Time:< /strong> &nbsp\; 12:00 pm &ndash\; 1:00 pm Eastern Time</p>\n<p><strong>&n bsp\;&nbsp\; Location:</strong>&nbsp\; Saint Maurice\, Trois Rivieres\, Qu ebec</p>\n<p><strong>&nbsp\;&nbsp\; ZOOM : <span style="background-color: #ffffff\;">https://uqtr.zoom.us/j/89805026456?pwd=bzluWlp0elY3clJzY0szYXpy a2pZdz09</span></strong></p>\n<p><strong>&nbsp\;&nbsp\; <span style="backg round-color: #ffffff\;">Meeting ID: 898 0502 6456 Password: 237973</span>< /strong></p>\n<p><strong><span style="background-color: #00ccff\;">ABSTRAC T</span> </strong></p>\n<p>&nbsp\;&nbsp\; Machine learning and deep learni ng tools have been rapidly advancing in capabilities over the past 7 years &ndash\; they have transformed the fields of computer vision\, speech\, n atural language processing\, and control systems in complex environments b y scaling to systems which can learn from massive sets of real-world data and feedback.&nbsp\;&nbsp\; More recently\, in the past 4 years\, radio si gnal processing and communications systems have been beginning to undergo this same transformation &ndash\; from relatively compact analytic system and world models to rich data-driven representations of signals\, impairme nts\, channel phenomenon\, and otherwise.&nbsp\;&nbsp\; Recent IEEE initia tive such as the IEEE Machine Learning for Communications (MLC) Emerging T echnology Area (ETI) have focused on highlighting and adapting ComSoc to s ome of these new challenging and embracing this approach for a number of p roblems.</p>\n<p>&nbsp\;&nbsp\; Our work at DeepSig and Virginia Tech has focused heavily on transitioning data-driven baseband radio processing tec hniques for communications systems in point-to-point\, mesh\, 5G\, and 6G systems to data-driven end-to-end learned models\, and leveraging data-dri ven deep learning models for real-time sensing and sense-making of radio s pectrum activity &ndash\; consuming high rates of raw sensor data and turn ing it into useful analytics\, mapping\, anomaly detection\, and real time information to enable scheduling and reactivity in the radio access netwo rk.&nbsp\;&nbsp\;</p>\n<p>&nbsp\;&nbsp\; This talk will highlight key enab lers which the communications society has begun to embrace\, will discuss the trade-offs and pros and cons of model driven\, data-driven\, and joint model/data-driven methods for signal processing. We will highlight a numb er of key works in this area\, highlighting where data-driven methods in c ommunications are highly effective\, and some areas where et hey are not. We will give a deep dive on how we are applying data-driven communications systems to several immediate and pertinent industry applications\, specul ate about where things are going\, and how the fields of communications\, signal processing\, information theory\, and machine learning will continu e to co-evolve and lead to exciting new opportunities and research.</p>\n< p>&nbsp\;</p>\n<p><strong>By</strong>&nbsp\;<strong>Dr. Tim O&rsquo\;Shea\ , Co-Founder/CTO of DeepSig </strong></p>\n<p>&nbsp\;</p> END:VEVENT END:VCALENDAR