BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20230312T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20231105T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20231101T012324Z UID:32E0EBFC-5E39-431A-A5A7-30690BAEE90A DTSTART;TZID=America/New_York:20231007T133000 DTEND;TZID=America/New_York:20231028T163000 DESCRIPTION:October 7 through October 28\, 2023. Saturdays 1:30-4:30pm.\n\n The IEEE North Jersey Section Communications Society (ComSoc chapter) is o ffering a course entitled "INTRODUCTION TO DEEP LEARNING".\n\nDeep learnin g is a transformative field within artificial intelligence and machine lea rning that has revolutionized our ability to solve complex problems in var ious domains\, including computer vision\, natural language processing\, a nd reinforcement learning. This introductory course on deep learning is de signed to provide students with an understanding how these amazing success es are made possible by drawing inspiration from the way that brains\, bot h human and otherwise\, operate. Students will gain a comprehensive founda tion in the principles\, techniques\, and applications of deep neural netw orks.\n\nThe IEEE North Jersey Section's Communications Society Chapter ca n arrange for providing IEEE CEUs - Continuing Education Units (for a $5 c harge) upon completion of the course. Course prices: $75 for Undergrad/Gra d/Life/ComSoc members\, $100 for IEEE members\, $150 for non-IEEE members\ n\nCo-sponsored by: Education Committee\n\nSpeaker(s): Thomas Long\, \n\nA genda: \nTopics and agenda:\n1. Fundamental Concepts: Explore the fundamen tal concepts of artificial neural networks\, backpropagation\, activation functions\, and gradient descent\, laying the groundwork for deep learning understanding.\n\nFamiliarize students with popular deep learning framewo rks such as TensorFlow and PyTorch\, enabling hands-on experience in model development and training.\n\nExamine a variety of neural network architec tures\, including feedforward networks\, convolutional neural networks (CN Ns) and recurrent neural networks (RNNs).\n\n2. Training Deep Neural Netwo rks: Study techniques for training deep neural networks effectively\, incl uding optimization algorithms\, weight initialization\, regularization\, a nd dropout.\n\nLearn data preprocessing techniques and best practices for preparing datasets for deep learning tasks\, including data augmentation a nd normalization.\n\n3. Computer Vision Applications: Apply deep learning to computer vision problems\, including image classification\, object dete ction\, and image generation using generative adversarial networks (GANs). \n\n4. Natural Language Processing (NLP): Explore how deep learning is use d in NLP tasks such as sentiment analysis\, machine translation\, and text generation.\n\nThis course assumes a basic understanding of machine learn ing concepts and programming skills in Python. Familiarity with linear alg ebra and calculus will be beneficial\, but not mandatory. Statistical soft ware (Python\, Scikit-learn) and Deep Learning Frameworks (Pytorch\, Tenso rFlow) will be used throughout the course for the exploration of different learning algorithms and for the creation of appropriate graphics for anal ysis.\n\nLearning objectives: Subjects covered include these and other dee p learning related materials: artificial neural networks\, training deep n eural networks\, RNN\, CNN\, image recognition\, natural language processi ng\, GANs\, data processing techniques\, and NN architectures.\n\nThe cour se is intended to be subdivided into 3-hour sessions. Each lecture is furt her subdivided into lecture\, guided and independent project based exercis es to build experience with hands-on techniques. This course will be held at FDU - Teaneck\, NJ campus. Checks should NOT be mailed to this address. Can bring checks in person or use online payments at registration. Email the organizer for any questions about course\, registration\, or other iss ues.\n\nTechnical Requirements: Students will need access to the Python pr ogramming language. In addition to a standard Python installation\, most p rogramming exercises will use the package Scikit-learn. Basic programming skills and some familiarity with the Python language are assummed.\nStuden ts are expected to be able to bring a laptop onto which most of these libr aries can be pre-installed using python's pip install.\n\nMost of the codi ng in this course will use the Python programming language. Coding example s and labs will be distributed in the form of Juypter notebooks. In additi on to standard Python\, most programming exercises will use either the PyT orch or TensorFlow libraries.\n\nRoom: Room BEC 205\, Bldg: Becton Buildin g \, FDU Metropolitan Campus\, 960 River Road\, Teaneck\, New Jersey\, Uni ted States\, 07666 LOCATION:Room: Room BEC 205\, Bldg: Becton Building \, FDU Metropolitan Cam pus\, 960 River Road\, Teaneck\, New Jersey\, United States\, 07666 ORGANIZER:a.j.patel@ieee.org SEQUENCE:33 SUMMARY:Introduction To Deep Learning URL;VALUE=URI:https://events.vtools.ieee.org/m/373452 X-ALT-DESC:Description: <br /><p>October 7 through October 28\, 2023. Satur days 1:30-4:30pm.&nbsp\;&nbsp\;</p>\n<p>The IEEE North Jersey Section Comm unications Society (ComSoc chapter) is offering a course entitled "INTRODU CTION TO DEEP LEARNING".&nbsp\;</p>\n<p>Deep learning is a transformative field within artificial intelligence and machine learning that has revolut ionized our ability to solve complex problems in various domains\, includi ng computer vision\, natural language processing\, and reinforcement learn ing. This introductory course on deep learning is designed to provide stud ents with an understanding how these amazing successes are made possible b y drawing inspiration from the way that brains\, both human and otherwise\ , operate. Students will gain a comprehensive foundation in the principles \, techniques\, and applications of deep neural networks.</p>\n<p>The IEEE North Jersey Section's Communications Society Chapter can arrange for pro viding IEEE CEUs - Continuing Education Units (for a $5 charge) upon compl etion of the course.&nbsp\; Course prices: $75 for Undergrad/Grad/Life/Com Soc members\, $100 for IEEE members\, $150 for non-IEEE members</p><br />< br />Agenda: <br /><p>Topics and agenda:<br />1. Fundamental Concepts: Exp lore the fundamental concepts of artificial neural networks\, backpropagat ion\, activation functions\, and gradient descent\, laying the groundwork for deep learning understanding.</p>\n<p>Familiarize students with popular deep learning frameworks such as TensorFlow and PyTorch\, enabling hands- on experience in model development and training.</p>\n<p>Examine a variety of neural network architectures\, including feedforward networks\, convol utional neural networks (CNNs) and recurrent neural networks (RNNs).</p>\n <p>2. Training Deep Neural Networks: Study techniques for training deep ne ural networks effectively\, including optimization algorithms\, weight ini tialization\, regularization\, and dropout.</p>\n<p>Learn data preprocessi ng techniques and best practices for preparing datasets for deep learning tasks\, including data augmentation and normalization.</p>\n<p>3. Computer Vision Applications: Apply deep learning to computer vision problems\, in cluding image classification\, object detection\, and image generation usi ng generative adversarial networks (GANs).</p>\n<p>4. Natural Language Pro cessing (NLP): Explore how deep learning is used in NLP tasks such as sent iment analysis\, machine translation\, and text generation.</p>\n<p>This c ourse assumes a basic understanding of machine learning concepts and progr amming skills in Python. Familiarity with linear algebra and calculus will be beneficial\, but not mandatory.&nbsp\;&nbsp\;Statistical software (Pyt hon\, Scikit-learn) and Deep Learning Frameworks (Pytorch\, TensorFlow) wi ll be used throughout the course for the exploration of different learning algorithms and for the creation of appropriate graphics for analysis.</p> \n<p>Learning objectives:&nbsp\; Subjects covered include these and other deep learning related materials: artificial neural networks\, training dee p neural networks\, RNN\, CNN\, image recognition\, natural language proce ssing\, GANs\, data processing techniques\, and NN architectures.</p>\n<p> The course is intended to be subdivided into 3-hour sessions. Each lecture is further subdivided into lecture\, guided and independent project based exercises to build experience with hands-on techniques.&nbsp\; This cours e will be held at FDU - Teaneck\, NJ campus.&nbsp\; Checks should NOT be m ailed to this address.&nbsp\; Can bring checks in person or use online pay ments at registration.&nbsp\; Email the organizer for any questions about course\, registration\, or other issues.</p>\n<p>Technical Requirements: S tudents will need access to the Python programming language. In addition t o a standard Python installation\, most programming exercises will use the package Scikit-learn. &nbsp\;Basic programming skills and some familiarit y with the Python language are assummed.<br />Students are expected to be able to bring a laptop onto which most of these libraries can be pre-insta lled using python's pip install.</p>\n<p>Most of the coding in this course will use the Python programming language. Coding examples and labs will b e distributed in the form of Juypter notebooks. In addition to standard Py thon\, most programming exercises will use either the PyTorch or TensorFlo w libraries.</p> END:VEVENT END:VCALENDAR