Lecture 2: Science and Research
Instructor: John Gabrieli
View the complete course: http://ocw.mit.edu/9-00SCS11

License: Creative Commons BY-NC-SA
More information at http://ocw.mit.edu/terms
More courses at http://ocw.mit.edu

Deep learning currently provides state-of-the-art performance in computer vision, natural language processing, and many other machine learning tasks. In this talk, we will learn when deep learning is useful (and when it isn't!), how to implement some simple neural networks in Python using Theano, and how to build more powerful systems using the OpenDeep package.

Our first model will be the 'hello world' of deep learning - the multilayer perceptron. This model generalizes logistic regression as your typical feed-forward neural net for classification.

Our second model will be an introduction to unsupervised learning with neural nets - the denoising auto-encoder. This model attempts to reconstruct corrupted inputs, learning a useful representation of your input data distribution that can deal with missing values.

Finally, we will explore the modularity of neural nets by implementing an image-captioning system using the the OpenDeep package.

Markus Beissinger
Recent graduate from the Jerome Fisher Program in Management and Technology dual degree program at the University of Pennsylvania (The Wharton School and the School of Engineering and Applied Science), and current Master's student in computer science. Focus on machine learning, startups, and management.

Slides: http://goo.gl/P9QGnV

The video focuses how to get started but particularly on the prompt engineering part to give you ideas and inspiration to what you can explore. Since Stable Diffusion was released couple of days ago this has been incorporated into MidJourney too which you can access by "—beta" argument which supposedly helps with face quality.

Resources mentioned:
https://github.com/willwulfken..../MidJourney-Styles-a

https://pitch.com/v/DALL-E-prompt-book-v1-tmd33y

https://docs.google.com/docume....nt/d/11WlzjBT0xRpQhP

Timestamps:
0:00 - Introduction to MJ and what you can do
8:17 - Resources for prompt inspiration
12:30 - How to iterate on the prompt/caption (prompt engineering)
29:40 - Other arguments you can use
32:26 - Final images result
33:25 - Ending

If deep neural networks are so powerful, why aren’t they used more often? The reason is that they are very difficult to train due to an issue known as the vanishing gradient.

Deep Learning TV on
Facebook: https://www.facebook.com/DeepLearningTV/
Twitter: https://twitter.com/deeplearningtv

To train a neural network over a large set of labelled data, you must continuously compute the difference between the network’s predicted output and the actual output. This difference is called the cost, and the process for training a net is known as backpropagation, or backprop. During backprop, weights and biases are tweaked slightly until the lowest possible cost is achieved. An important aspect of this process is the gradient, which is a measure of how much the cost changes with respect to a change in a weight or bias value.

Backprop suffers from a fundamental problem known as the vanishing gradient. During training, the gradient decreases in value back through the net. Because higher gradient values lead to faster training, the layers closest to the input layer take the longest to train. Unfortunately, these initial layers are responsible for detecting the simple patterns in the data, while the later layers help to combine the simple patterns into complex patterns. Without properly detecting simple patterns, a deep net will not have the building blocks necessary to handle the complexity. This problem is the equivalent of to trying to build a house without the proper foundation.

Have you ever had this difficulty while using backpropagation? Please comment and let me know your thoughts.

So what causes the gradient to decay back through the net? Backprop, as the name suggests, requires the gradient to be calculated first at the output layer, then backwards across the net to the first hidden layer. Each time the gradient is calculated, the net must compute the product of all the previous gradients up to that point. Since all the gradients are fractions between 0 and 1 – and the product of fractions in this range results in a smaller fraction – the gradient continues to shrink.

For example, if the first two gradients are one fourth and one third, then the next gradient would be one fourth of one third, which is one twelfth. The following gradient would be one twelfth of one fourth, which is one forty-eighth, and so on. Since the layers near the input layer receive the smallest gradients, the net would take a very long time to train. As a subsequent result, the overall accuracy would suffer.

Credits
Nickey Pickorita (YouTube art) -
https://www.upwork.com/freelan....cers/~0147b8991909b2
Isabel Descutner (Voice) -
https://www.youtube.com/user/IsabelDescutner
Dan Partynski (Copy Editing) -
https://www.linkedin.com/in/danielpartynski
Jagannath Rajagopal (Creator, Producer and Director) -
https://ca.linkedin.com/in/jagannathrajagopal

ChatGPT has taken the world by storm and GPT4 is out soon. While that’s great, wouldn't you like to run your own chatbot, locally and for free (unlike GPT4)? No more queues, nothing to pay, a choice of models and the ability to create your own characters? What’s that? It doesn’t even need a GPU? Sounds too good to be true? Welcome to the text-generation-webui! A gradio web UI for running Large Language Models like GPT-J 6B, OPT, GALACTICA, LLaMA, Pygmalion and many, many more! Whisper and TTS included, allowing you to speak to your characters and have them speak back too.

As with anything AI, you’ll have the very best experience of a simple, error free install every time on Linux.
For Microsoft Windows the exact same steps should also work, but as any Windows user knows anything could go wrong at any time!
As for Mac - not sure!

Thanks to huggingface there is a massive library of models, many with Open Source licenses just ready for you to use! Create any custom character you like and take it for a spin - even with just 8GB VRAM. Some models work with much less too 😀

If you don’t like standard installations, you can also use the obfuscated method. It’s just 3 steps:
1. Install using the 1-click installer
2. Download your model(s)
3. Start the webui!

See the pinned tweet for more links ;)

I’m pretty sure everyone will want to try this, so expect to see lots more of this interface as others catch on! Just remember where you saw it first - right here on the Nerdy Rodent channel!

== Links! ==
* Installing Anaconda for MS Windows Beginners - https://youtu.be/OjOn0Q_U8cY
* How do I create an animated SD avatar? - https://youtu.be/Z7TLukqckR0
* Stable Diffusion Playlist! - https://youtube.com/playlist?l....ist=PLjC8P1vEncQDVOC

== Stable Diffusion Playlists ==
* Interested in adding things to your AI Art? Try these!
Dreambooth Playlist - https://youtube.com/playlist?l....ist=PLjC8P1vEncQD-QY
* Textual Inversion Playlist - https://youtube.com/playlist?l....ist=PLjC8P1vEncQDSDL

Note that GitHub repositories update often! Be sure to check the GitHub README for the current info ;)m

🔥𝐄𝐝𝐮𝐫𝐞𝐤𝐚 𝐏𝐲𝐭𝐡𝐨𝐧 𝐂𝐞𝐫𝐭𝐢𝐟𝐢𝐜𝐚𝐭𝐢𝐨𝐧 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐂𝐨𝐮𝐫𝐬𝐞 : https://www.edureka.co/python-....programming-certific (Use code "𝐘𝐎𝐔𝐓𝐔𝐁𝐄𝟐𝟎")
This Edureka video on the "How to Create Login System using Python" will help you in building a login system in a step by step manner.
Topics covered in this video:
00:00:00 Introduction
00:00:17 Agenda
00:00:43 What is Python
00:01: 51 Features of Python
00:05:24 Who uses Python
00:05:41 What is a Login System
00:06:03 Prerequisites for Login System
00:06:33 Python Login System Project Objective
00:07:58 Login Authentication
00:08:22 New Users Registration
00:08:39 Hands-On

🔴 Subscribe to our channel to get video updates. Hit the subscribe button above: https://goo.gl/6ohpTV

📝Feel free to share your comments below.📝

🔴 𝐄𝐝𝐮𝐫𝐞𝐤𝐚 𝐎𝐧𝐥𝐢𝐧𝐞 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐚𝐧𝐝 𝐂𝐞𝐫𝐭𝐢𝐟𝐢𝐜𝐚𝐭𝐢𝐨𝐧𝐬

🔵 DevOps Online Training: http://bit.ly/3VkBRUT
🌕 AWS Online Training: http://bit.ly/3ADYwDY
🔵 React Online Training: http://bit.ly/3Vc4yDw
🌕 Tableau Online Training: http://bit.ly/3guTe6J
🔵 Power BI Online Training: http://bit.ly/3VntjMY
🌕 Selenium Online Training: http://bit.ly/3EVDtis
🔵 PMP Online Training: http://bit.ly/3XugO44
🌕 Salesforce Online Training: http://bit.ly/3OsAXDH
🔵 Cybersecurity Online Training: http://bit.ly/3tXgw8t
🌕 Java Online Training: http://bit.ly/3tRxghg
🔵 Big Data Online Training: http://bit.ly/3EvUqP5
🌕 RPA Online Training: http://bit.ly/3GFHKYB
🔵 Python Online Training: http://bit.ly/3Oubt8M
🌕 Azure Online Training: http://bit.ly/3i4P85F
🔵 GCP Online Training: http://bit.ly/3VkCzS3
🌕 Microservices Online Training: http://bit.ly/3gxYqqv
🔵 Data Science Online Training: http://bit.ly/3V3nLrc
🌕 CEHv12 Online Training: http://bit.ly/3Vhq8Hj
🔵 Angular Online Training: http://bit.ly/3EYcCTe

🔴 𝐄𝐝𝐮𝐫𝐞𝐤𝐚 𝐑𝐨𝐥𝐞-𝐁𝐚𝐬𝐞𝐝 𝐂𝐨𝐮𝐫𝐬𝐞𝐬

🔵 DevOps Engineer Masters Program: http://bit.ly/3Oud9PC
🌕 Cloud Architect Masters Program: http://bit.ly/3OvueZy
🔵 Data Scientist Masters Program: http://bit.ly/3tUAOiT
🌕 Big Data Architect Masters Program: http://bit.ly/3tTWT0V
🔵 Machine Learning Engineer Masters Program: http://bit.ly/3AEq4c4
🌕 Business Intelligence Masters Program: http://bit.ly/3UZPqJz
🔵 Python Developer Masters Program: http://bit.ly/3EV6kDv
🌕 RPA Developer Masters Program: http://bit.ly/3OteYfP
🔵 Web Development Masters Program: http://bit.ly/3U9R5va
🌕 Computer Science Bootcamp Program : http://bit.ly/3UZxPBy
🔵 Cyber Security Masters Program: http://bit.ly/3U25rNR
🌕 Full Stack Developer Masters Program : http://bit.ly/3tWCE2S
🔵 Automation Testing Engineer Masters Program : http://bit.ly/3AGXg2J
🌕 Python Developer Masters Program : https://bit.ly/3EV6kDv
🔵 Azure Cloud Engineer Masters Program: http://bit.ly/3AEBHzH

🔴 𝐄𝐝𝐮𝐫𝐞𝐤𝐚 𝐔𝐧𝐢𝐯𝐞𝐫𝐬𝐢𝐭𝐲 𝐏𝐫𝐨𝐠𝐫𝐚𝐦𝐬

🌕 Post Graduate Program in DevOps with Purdue University: https://bit.ly/3Ov52lT

🔵 Advanced Certificate Program in Data Science with E&ICT Academy, IIT Guwahati: http://bit.ly/3V7ffrh

🔵 Advanced Certificate program in Cloud Computing : https://bit.ly/43vmME8

📌𝐓𝐞𝐥𝐞𝐠𝐫𝐚𝐦: https://t.me/edurekaupdates
📌𝐓𝐰𝐢𝐭𝐭𝐞𝐫: https://twitter.com/edurekain
📌𝐋𝐢𝐧𝐤𝐞𝐝𝐈𝐧: https://www.linkedin.com/company/edureka
📌𝐈𝐧𝐬𝐭𝐚𝐠𝐫𝐚𝐦: https://www.instagram.com/edureka_learning/
📌𝐅𝐚𝐜𝐞𝐛𝐨𝐨𝐤: https://www.facebook.com/edurekaIN/
📌𝐒𝐥𝐢𝐝𝐞𝐒𝐡𝐚𝐫𝐞: https://www.slideshare.net/EdurekaIN
📌𝐂𝐚𝐬𝐭𝐛𝐨𝐱: https://castbox.fm/networks/505?country=IN
📌𝐌𝐞𝐞𝐭𝐮𝐩: https://www.meetup.com/edureka/
📌𝐂𝐨𝐦𝐦𝐮𝐧𝐢𝐭𝐲: https://www.edureka.co/community/

Please write back to us at [email protected] or call us at IND: 9606058406 / US: 18338555775 (toll-free) for more information.

Get 20% off NVIDIA certification exams using the code "TechWithTim20" from here: https://nvda.ws/46Sehq8

Today we're diving deep into one of the hottest topics in AI right now. Building actual agents in Python. Not just chat bots to respond to your queries, but autonomous systems with memory goals and the ability to take actions in the world.

Want to make real money with coding? I share high-signal insights on careers, monetization, and leverage in my free newsletter. Join here and get my guide How to Make Money With Coding instantly: https://techwithtim.net/newsletter

⏳ Timestamps ⏳
00:00 | AI Agents
00:37 | NVIDIA Free AI Courses
01:38 | AI Agent Building Blocks
05:30 | Python Frameworks
09:01 | Python Tools
09:40 | AI Agent Patterns
13:15 | Picking Your Stack

Hashtags
#Nvidia #AiAgents #Python

MIT 15.773 Hands-On Deep Learning Spring 2024
Instructor: Rama Ramakrishnan
View the complete course: https://ocw.mit.edu/courses/15....-773-hands-on-deep-l
YouTube Playlist: https://www.youtube.com/playli....st?list=PLUl4u3cNGP6

Continues discussion of natural language processing with a focus on embeddings, including stand-alone and contextual embeddings.

License: Creative Commons BY-NC-SAMore information at https://ocw.mit.edu/termsMore courses at https://ocw.mit.eduSupport OCW at http://ow.ly/a1If50zVRlQ

We encourage constructive comments and discussion on OCW’s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https://ocw.mit.edu/comments.

Host Your AI Agent with Hostinger 👉 https://www.hostg.xyz/SHJwM

In this video, I explain how AI agents work, then show how to deploy Hermes on a Hostinger VPS, connect it to OpenRouter and Telegram, give it scheduled jobs, use persistent memory and learned skills, and keep the agent secure and inexpensive while it runs around the clock.

Grab The AI Agent Build Kit 👉 https://youri-van-hofwegen.kit.com/35ac6b24d1

for inquiries: roboverse at youripartnerships.com

#Roboverse

#8K #BIRD #ANIMALS
THE World's Greatest Birds HD 8K ULTRA - Relaxing Music And Nature 8K TV

Birds belong to the group of vertebrates and are a species with wings that mostly allow them to fly, although there are also a few species of birds that cannot.
In general, birds fly, jump, walk or swim with amazing speed and agility. What's amazing is what happens during the breeding season. For centuries, the courtship of these species has amazed humans.
The size of the birds varies between species, they can measure from 6.4 cm for small hummingbirds, to about 2.74 meters in ostriches, the largest bird in the world.
The bird has a horn beak and no teeth. They are warm-blooded, able to walk, run, and stand on only their hind limbs.
Their forelimbs are reshaped with wings, allowing them, in most birds, to fly.
Flight is the primary means of transportation for most birds, and they also use it to breed, feed, and flee from predators.
However, about 60 species of flightless birds are often found on isolated islands, possibly due to resource scarcity and the absence of terrestrial predators.
Communication between birds is very flexible and can include sensory cues, calls, and songs. Some make a variety of sounds and calls.
The bird's diet consists of a large amount of food such as nectar, fruits, plants, seeds, carcasses and various small animals, including other birds. However, the diet varies by species.
Birds inhabit all lands and all oceans of the world. They are even found in the Antarctic region.
Birds often migrate to take advantage of seasonal temperature differences around the world. Migration varies widely by sex.
There are over 9,000 different types or species of birds on the planet.

#scenicrelaxation #8kvideo #relaxationmusic #relaxationfilm #8kvideoultrahd
------------------------------

🌿Welcome to the new relaxing music stream on Scenic Relaxation 8K channel. You can keep the video at low volume and start doing any work like studying, working, reading… or simply relaxing or getting a good night's sleep.

🌿Music to relax, meditate, study, read, massage, spa or sleep. This type of music is ideal to combat anxiety, stress or insomnia as it facilitates relaxation and helps us to get rid of bad vibrations. You can also use this music as a background for guided meditation classes or sleep relaxation.

🌿If you enjoyed the live stream and want more relaxing music content, don't forget to like and subscribe!

------------------------------
🎹More soothing music on Spotify playlist: https://spoti.fi/38bwOia

🌿Follow Helios Record for new release every week:
➤ Spotify: https://spoti.fi/2OgiA6M
➤ SoundCloud: https://bit.ly/1V3lGKg
➤Youtube: https://bit.ly/2BQ5Y3D
➤ Instagram: https://bit.ly/2Zjztnc
➤ Facebook: https://bit.ly/2ZhUKgV

Music By:
🌿Follow Helios Record :
➤ Spotify: https://spoti.fi/2YNxyG6
➤ Soundcloud: https://soundcloud.com/heliosrecord
➤ Instagram: https://www.instagram.com/helios.record/
➤ Facebook: https://www.facebook.com/Helios-Recor...

🌿 Music by Vincent Carry
➤ Spotify:https://spoti.fi/2ZSgDCA

------------------------------

"🌞 For contact and submit music: [email protected]

►All rights belong to their respective owners.
✔ This video was given a special license directly from the artists and the right holders."

In this video we take a look at how to solve the super common problem of having an imbalanced or skewed dataset, specifically we look at two methods namely oversampling and class weighting and how to do them both in PyTorch.

Toy dataset used in video:
https://www.kaggle.com/dataset..../77934f795ab14e30431

People often ask what courses are great for getting into ML/DL and the two I started with is ML and DL specialization both by Andrew Ng. Below you'll find both affiliate and non-affiliate links if you want to check it out. The pricing for you is the same but a small commission goes back to the channel if you buy it through the affiliate link.
ML Course (affiliate): https://bit.ly/3qq20Sx
DL Specialization (affiliate): https://bit.ly/30npNrw
ML Course (no affiliate): https://bit.ly/3t8JqA9
DL Specialization (no affiliate): https://bit.ly/3t8JqA9

GitHub Repository:
https://github.com/aladdinpers....son/Machine-Learning

✅ Equipment I use and recommend:
https://www.amazon.com/shop/aladdinpersson

❤️ Become a Channel Member:
https://www.youtube.com/channe....l/UCkzW5JSFwvKRjXABI

✅ One-Time Donations:
Paypal: https://bit.ly/3buoRYH
Ethereum: 0xc84008f43d2E0bC01d925CC35915CdE92c2e99dc

▶️ You Can Connect with me on:
Twitter - https://twitter.com/aladdinpersson
LinkedIn - https://www.linkedin.com/in/al....addin-persson-a95384
GitHub - https://github.com/aladdinpersson

PyTorch Playlist:
https://www.youtube.com/playli....st?list=PLhhyoLH6Ijf

🔥 CSPO® Certification Training: https://www.edureka.co/cspo-certification-training **
This Edureka video on "Product Owner Interview Questions" will help you prepare for your scrum job interviews. The topics discussed in this course are listed below:
Beginner Level Product Owner Interview Questions
Advances Level Product Owner Interview Questions
Comparison Based Product Owner Interview Questions
Real-World Scenario Based Product Owner Interview Questions

- - - - - - - - - - - - - - - - -

Join Edureka’s Meetup community and never miss any event – YouTube Live, Webinars, Workshops etc. https://bit.ly/2EfTXS1

Subscribe to our channel to get video updates. Hit the subscribe button above: https://goo.gl/6ohpTV

SlideShare: https://www.slideshare.net/edurekaIN
Instagram: https://www.instagram.com/edureka_learning/
Facebook: https://www.facebook.com/edurekaIN/
Twitter: https://twitter.com/edurekain
LinkedIn: https://www.linkedin.com/company/edureka

---------------------------------------------------------------------------------

#edureka #EdurekaCSPO #productownerinterviewquestions #scrumproductowner #scrumedureka #scrum #productowner #agile #scrumtraining

About the Course

Scrum is an Agile Project Management Framework that can be used primarily to manage iterative and incremental projects of all types. In this course, you will learn Agile Project Management with Scrum. You will be given an overview of the principles and practices that make Scrum effective at managing projects.
At the end of the course, you will have the confidence and understanding to implement Scrum in your organization and support teams in improving their processes.

1. Get a brief introduction to Agile and Scrum methodology
2. Understand the advantages of Agile over traditional methods
3. Get to know the core practices and philosophies behind Scrum Framework
4. Learn about Roles, Events and Artifacts, and the Process flow
---------------------------------------------------------------------------------
Who should go for the course?

1. Developers
2. Project Managers
3. Managers-Software Development
4. Architects-Software Development
5. Product Managers
6. Software Developers
7. Software Coders
8. Software Testers

--------------------------------------------------------------------------

For more information, Please write back to us at [email protected] or call us at IND: 9606058406 / US: 18338555775 (toll free).

#ai #artificialintelligence #chatgpt #midjourney #llm #largelanguagemodels #largelanguagemodel

This is a short and very simple video I created to explain some of the concepts that go into large language models like Chat-GPT4. It covers various aspects of LLM artificial intelligence like foundations, architecture, pre-training, fine-tuning, tokenization, embeddings, self-attention, positional encoding, layers and headers, and decoding. The text was created with the use of chat gpt4. All of the images were created using Midjourney AI based on the text.

🔥Professional Certificate Program in Generative AI and Machine Learning - IITG (India Only) - https://www.simplilearn.com/iitg-generative-ai-machine-learning-program?utm_campaign=labxPbQ88Zk&utm_medium=DescriptionFirstFold&utm_source=Youtube
🔥Purdue - Ai And Machine Learning Post Graduate Certificate Program - https://www.simplilearn.com/applied-ai-course?utm_campaign=labxPbQ88Zk&utm_medium=DescriptionFirstFold&utm_source=Youtube

In this video on openAI chatgpt 4o, we will be exploring the latest open ai model gpt4o, in this we will cover what is gpt40, how it different from the other gpt mode, chatgpt features demo like chitchatting with gpt, uploading image etc, at the end we will cover safety and limitations of gpt 4o.
GPT-4o is a big upgrade in OpenAI's smart tech. It's better at understanding and talking like a human than previous versions. It's super good at tasks like answering questions or writing stories. OpenAI keeps making it better. Now, it can even understand pictures! This makes it even more useful.

Below are the topics covered in how to use chatgpt 4o video:

00:00 Introduction To Open AI ChatGPT-4o
00:24 What Is Gpt 4o
02:21 How Gpt 4o is different from other models
02:44 Chatgpt 4o Demo Features
11:25 Safety and limitations of gpt 4o

✅Subscribe to our Channel to learn more about the top Technologies: https://bit.ly/2VT4WtH

#chatgpt4o # GPT4o #AI #ArtificialIntelligence #MachineLearning #2024 #Simplilearn

⏩ Check out More AI Videos By Simplilearn: https://www.youtube.com/watch?v=ad79nYk2keg&list=PLEiEAq2VkUULyr_ftxpHB6DumOq1Zz2hq&pp=gAQBiAQB

➡️ About Artificial Intelligence Engineer

This Artificial Intelligence Engineer course Created in partnership with IBM, this course introduces students to blended learning and prepares them to be AI and Data Science specialists. In Armonk, New York, IBM is a significant cognitive service and integrated cloud solution firm that provides many technology and consulting solutions.

IBM is a leader in AI and Machine Learning technology verticals for 2021. This AI masters course will prepare students for Artificial Intelligence and Data Analytics careers.

✅ Key Features

- Add the IBM Advantage to your Learning
- 25 Industry-relevant Projects and Integrated labs
- Immersive Learning Experience
- Simplilearn's JobAssist helps you get noticed by top hiring companies

✅ Skills Covered

- ChatGPT
- Flask
- Matplotlib
- django
- Python
- Numpy
- Pandas
- SciPy
- Keras
- OpenCV
- And Many More…

👉 Enroll Now: https://www.simplilearn.com/pgp-ai-machine-learning-certification-training-course?utm_campaign=17May24ChatGPT4o&utm_medium=Description&utm_source=youtube
🔥🔥 *Interested in Attending Live Classes? Call Us:* IN - 18002127688 / US - +18445327688