- Видео 60
- Просмотров 436 532
Pritish Mishra
Индия
Добавлен 24 авг 2013
I know some machine learning
I trained an LLM on my WhatsApp Chats
Join On-Demand Waitlist now: on-demand.io/contact
In this video, I trained an AI chatbot to impersonate me on WhatsApp and see if it could fool my friends into thinking they were talking to the real me. I call this AI chatbot "PriBot" and I trained it using my extensive WhatsApp chat history, fine-tuning a large language model to adopt my unique writing style, humor, and personality.
I then set PriBot loose in live WhatsApp conversations with my friends, letting it take over the chat and try to pass the "Turing Test" by convincing them they were talking to the actual me. Overall though, PriBot was able to have fairly natural and coherent conversations, leaving my friends often unsure if the...
In this video, I trained an AI chatbot to impersonate me on WhatsApp and see if it could fool my friends into thinking they were talking to the real me. I call this AI chatbot "PriBot" and I trained it using my extensive WhatsApp chat history, fine-tuning a large language model to adopt my unique writing style, humor, and personality.
I then set PriBot loose in live WhatsApp conversations with my friends, letting it take over the chat and try to pass the "Turing Test" by convincing them they were talking to the actual me. Overall though, PriBot was able to have fairly natural and coherent conversations, leaving my friends often unsure if the...
Просмотров: 893
Видео
I built a real-time AI that mimics my movements in Super Mario
Просмотров 1,1 тыс.7 месяцев назад
Twitter: PritishllM Instagram: pritishmishra703 LinkedIn: www.linkedin.com/in/pritish31/ Code: github.com/pritishmishra703/MarioIRL Dive into this gaming experiment with me as I figure out how to control Mario using just my body! I'll take you through the hurdles of tracking my movements without a camera, creating a cool Android app for real-time sensor data, and trai...
Automate Anything using ChatGPT!
Просмотров 1,7 тыс.Год назад
GitHub Repo: github.com/pritishmishra703/Luna In this video, we embark on the journey of creating our own computer assistant named Luna. Utilizing ChatGPT and speech-to-intent classification, we develop Luna's abilities to understand user commands and perform tasks such as opening websites, desktop applications, and even simulating keyboard shortcuts. With the integration of a wake word detecto...
Using GPT-3 to Generate Answers From Book
Просмотров 10 тыс.Год назад
HuggingFace Space: huggingface.co/spaces/pritish/BookGPT Kaggle Notebook: bit.ly/3kg3dP7 Have you ever wished you could search a book like you search the web? In this video, we'll show you how to build an AI book search using the Universal Sentence Encoder and GPT-3. We'll walk through the steps of breaking down a large book into smaller chunks, generating embeddings for each chunk using the Un...
The Secret to 90%+ Accuracy in Text Classification
Просмотров 46 тыс.Год назад
In this video, we will be providing a beginner's guide to fine-tuning BERT, one of the most powerful natural language processing (NLP) models available. BERT, which stands for "Bidirectional Encoder Representations from Transformers," has been trained on a massive amount of text data and can be fine-tuned for a variety of NLP tasks, such as text classification, machine translation, and named en...
How to Make Your Images Talk: The AI that Captions Any Image
Просмотров 54 тыс.Год назад
HuggingFace Web App: bit.ly/3SDyOWt Image captioning is the process of taking an image and generating a caption that accurately describes the scene. This is a difficult task for neural networks because it requires understanding both natural language and computer vision. In this video, I discuss my complete approach to this problem. For visual understanding, we will use Inception V3, and for nat...
The power of "Attention" in Deep Learning
Просмотров 2,1 тыс.2 года назад
In this video, we will learn about attention and how it can be used to improve machine translation. First, we will see how machine translation used to be done before attention was introduced. Then we will learn about Bahdanau attention and how it works. Finally, we will implement it with TensorFlow. Source code (GitHub): bit.ly/3Q4QitD 🔗 Social Media 🔗 📱 Twitter: bit.ly/3aJWAeF 📝 LinkedIn: bi...
NLP-based Movie Recommendation System
Просмотров 6 тыс.2 года назад
Hey, Google's Universal Sentence Encoder can generate embeddings for any sentence, which can be used to create a recommendation system for movies. The system uses the Top 10,000 movies dataset from Kaggle, which provides a short description of each movie. The system then generates embeddings for all 5,500 movies in the dataset and uses principal component analysis to visualize the embeddings in...
Data Augmentation with Albumentations (Python Package)
Просмотров 7 тыс.2 года назад
Hey, In this video, we will discuss Albumentations. It is a python package for augmentations. You must be thinking, "What's the need for a dedicated augmentation library when most of the deep learning frameworks already have support for augmentation?". Well, Albumentations is different it is very fast, easy to use, and most important you can do augmentation for Image segmentation, Object Detect...
The Convolutional Neural Network (Animated Introduction)
Просмотров 2,6 тыс.2 года назад
Hey, In this video, we will discuss the convolutional neural networks which are used for image datasets. Timestamp: 0:00-0:33 Introduction 0:33-0:54 How does image data look like? 0:54-1:45 Why can't we use ANN? 1:45-4:47 Convolutional neural network 4:47-5:41 Strides 5:41-7:01 Max-Pooling 7:01-8:31 The Final Picture 8:31-9:04 Outro Access this playlist: bit.ly/3kEjs4J Github Repo of playlist: ...
Early Stopping & Dropout: Ways to overcome Overfitting
Просмотров 8 тыс.2 года назад
Hey, In this video, we will discuss Early stopping and Dropout which is ways to overcome overfitting. Access this playlist: bit.ly/3kEjs4J Github Repo of playlist: bit.ly/3jy3r13 Resources: More about Dropout 1. bit.ly/3emITVH 2. bit.ly/3svDaFn 3. bit.ly/32gGn0Z 🔗 Social Media 🔗 📱 Twitter: bit.ly/3aJWAeF 📝 LinkedIn: - bit.ly/3aQGGiL 🌎 Website: bit.ly/31F4nb2 📂 GitHub: bit.ly/2QGLVYV ⭐ C...
What is a Deep Neural Network?
Просмотров 2,3 тыс.2 года назад
Hey, In this video, we will discuss Deep neural networks (DNN). Deep neural network is made up of neurons which are fundamental building blocks of a DNN. We will also discuss how DNN trains [forward and backward pass] and then implement this with Keras. Access this playlist: bit.ly/3kEjs4J Code of this video: bit.ly/32avAVD Github Repo of playlist: bit.ly/3jy3r13 Resources: More about Deep Neur...
Adam, AdaGrad & AdaDelta - EXPLAINED!
Просмотров 10 тыс.2 года назад
Hey, In this video, we will discuss what Adam optimizer is and go into some detail. This video also includes AdaGrad and AdaDelta optimizers. You might have used Adam in your standard deep learning workflow but knowing it's under the hood details is also essential. Access this playlist: bit.ly/3kEjs4J Code of this video: bit.ly/3n7XcBq Github Repo of playlist: bit.ly/3jy3r13 Timestamp: 0:00 - 0...
Optimization in Deep Learning
Просмотров 12 тыс.2 года назад
Hey, In this video, we will discuss what is optimization? with animation in a crystal clear way! We will discuss how optimization works and how it updates weights and biases to reduce the error made by the loss function. This video covers Gradient Descent, Momentum, the role of learning rate in training, live simulation of training with gradient descent, and types of Gradient descent. Access th...
See this if you DON'T understand Loss Functions
Просмотров 8222 года назад
See this if you DON'T understand Loss Functions
Activation Functions: The Intuitive way!
Просмотров 7163 года назад
Activation Functions: The Intuitive way!
Neuron: Building block of Deep learning
Просмотров 1,6 тыс.3 года назад
Neuron: Building block of Deep learning
K Nearest Neighbor Algorithm from Scratch (in 30 line) | Clearly Explained!
Просмотров 3,3 тыс.3 года назад
K Nearest Neighbor Algorithm from Scratch (in 30 line) | Clearly Explained!
Wake Word Detection with Tensorflow | P2
Просмотров 6 тыс.3 года назад
Wake Word Detection with Tensorflow | P2
Wake Word Detection with TensorFlow (100% Accuracy on Test Data!)
Просмотров 17 тыс.3 года назад
Wake Word Detection with TensorFlow (100% Accuracy on Test Data!)
L1 and L2 Regularization in Machine learning (Mathematics Explained!)
Просмотров 2,3 тыс.3 года назад
L1 and L2 Regularization in Machine learning (Mathematics Explained!)
Your Python Script to Pip Package in Minutes
Просмотров 2753 года назад
Your Python Script to Pip Package in Minutes
What is Label Encoder | Data Preprocessing - Machine Learning
Просмотров 4493 года назад
What is Label Encoder | Data Preprocessing - Machine Learning
The Timelapse | Artificial Intelligence
Просмотров 1903 года назад
The Timelapse | Artificial Intelligence
Make your OWN Linear Regression Algorithm - #1
Просмотров 2113 года назад
Make your OWN Linear Regression Algorithm - #1
Linear Regression Math Intution With Animation | ML Series Part 1
Просмотров 9463 года назад
Linear Regression Math Intution With Animation | ML Series Part 1
How to Search Content in Website with Django | Advance Django Tutorials - #11
Просмотров 4,2 тыс.3 года назад
How to Search Content in Website with Django | Advance Django Tutorials - #11
I am very impressed with the way you teach.
Great content keep it up 👏
Lesss gooo 🗿
nice 🗿🔥
AI 🚀🚀
Amazing Content , Keep it Up !!
Hii is there a way to augment a video dataset
Broo's video quality 🔥🔥🔥🔥
in rotation of phone 2 more sensors are used . not just accelerometer
why are you not famous yet,you are too good
This was great. We were supposed to build a model from the beginning like this at my university. But we stopped halfway through because of time constraints :( . Your videos were perfect. I liked and subscribed!
Source code link with RNN not working😢😢
How to fine tune csv dataset on BERT model
Hey i wanted to ask how did you start your journey .. I am willing to understand ML in depth with GenAi.. You prefer any courses pls let me know
Great work pritish! truly inspired by your dedication to deliver such amazing content
no one was covering this library , u r a legend bro ..! I knew data augmentation in CNN but yolo have labelled data ..!
Hey, great lecture! Just need a help, the link for the google colab for image captioning with rnn isn't working. It would be great help if you'll provide a new link. Thankyou!!
can be it possible online like on Character ai , that varun talking about
It is technical for me 😅 Sorry
Best explanation in a simple and easy way.
I'd like to ask, a paper I am trying to use for another dataset said they had optimal performance at epochs=50, however at epochs=3, it's already getting decent performance. May I ask why this is? Also, do you run bert in inference mode?
The video is not that great. You simply explained the formula without helping us understand how that penalty is derived. Thumbs down.
Great video, pls do make more such video
Your RNN file is showing Page Not Found , can you reupload the file
Awesome Video bro !! You explained Image captioning in a simple and fun way.
You killed it
Amazing work Pritish. You definitely deserve more views. Hopefully you will get it soon❤.
Nice, thx :D
After model.summary,() Output shape column showsquestion mark ? and param column shows unbuilt
Good job!
Hey, it's amazing! Is it open source,... Would love to see and contribute ❤
The code is currently a mess. I will soon push all the code to this repository: github.com/pritishmishra703/AI-WhatsApp-Clone. You can then contribute. Thank you.
Great video good job 👍
Yeah I am on RUclips 🫡😂😂
thanks dhiraj for participating in the video.
Nice video, thank you for sharing!!!!
hey none of your links are working
Very nice
Very nice explanation
Link of Images Captioning with RNN was dead, Can you update it to help me. Thank you. From VietNam with love <3
how to actually decode the output back to the classes is something this video did not explain : \
I have found that alpha_t gets too big too quickly so that learning slows to a crawl. A simple line search works better.
so we don't need to freeze any layer of the pretrained model? i have a problem this is with VIT my image shape is 24x24 but the pretrained model input shape is 224x224 it is possible to fix that? and the learning parameter are 8900000 and i want to fine tune it on my dataset
Beautiful Bro. Your soo smart..
Great vids.. you need more recognition, keep grinding man! I'm learning from u day by day
best explanation
I have tried your python notebook for this video from Github. Excellent work. Thanks for making it available. However, I can see that adam is not really working best for the linear function you have created. I was wondering, at what point of non-linear complexity does adam start showing better results over other optimizers. Would be great to have this discussion.
Bro can you share this full file please
You have so much potential, amazing!
Github link is not opening , it's says that it was uploaded from a suspended account
from the last 5-6 hrs i am trying to find a step-by-step proper material on how to fine to BERT with your dataset , finally found it , thank for making this video.
ur github link is saying that it is suspended