Відео

stellargraph is another good library too

After watching many LoRA videos, this one finally makes me satisfied. I have a question: I see in the fine tuning code, they talk about merging lora adapters. What is that? Is this h + = x @ (W_A @ W_B) * alpha ? Can you mix and match adapters to improve the evaluation score?

thanks

Isn't the embedding layer redundant? I mean we have then the projection matrices meaning that embedding + projection is a composition of two linear layers.

(rome is bigger than nyc)

Keep making content like this, I am sure you will get a very good recognition in the future. Thanks for such amazing content.

best

A great video as usual. Very detailed and comprehensive 😊. Only one thing left me confused: Why isn’t it a problem to making use of Euclidian distance in t-SNE and Umap? You could have assumed they skip it completely.

thank u a lot for all ur videos :D can u do one about graphsage ?

best explanation present out there, i would love to connect with you to gain some knowledge about the ML/AI journey i wanna go through, please tell me how can i connect with you?

Must-watch series for any CS major.

Thank you for the excellent presentation of the topic, a job well done!

thank you so much for the splendid explanation!

I have worst experience in your channel deep learning course videos are very less and your channel has worst audio clarity

This is the worst voice clarity i have experienced in the UA-cam and video editing you have to improve how can people understand

Your voice clarity is toooo worst

Awesome presentation, you should really be proud of this series! Learned quite a lot, and also learned how to transfer knowledge effectively. All the best!

Thank you. I think I understand now.

I have come to understand attention as key, query, value multiplication/addition. Do you know why this wasn't used and if it's appropriate to call it attention?

Excellent overview. Appreciate it!

There was a error on your published code but not in the video. attn_output, attn_output_weights = self.att(x, x, x) It should be attn_output, attn_output_weights = self.att(q, k, v) Anyway, thanks for sharing the video and code base. It helped me a lot while learning ViT

Great video. Amazing stuff. I have a query. In this use case, it is assumed the distance-based calculations formulate the edge index, and hence, it is constant. How we should proceed if the edges/edge indexes change for every time snapshot.

You are amazing at explaining. Congratulations at having done this so incredibly well

Hi, great video, thanks! Is there a way to use SHAP for ARIMA/SARIMA?

your content and explanation is Incredibly helpful. Thank you

Is this better for the MNIST challenge compared to a simple conv network like LeNet

Awesome!

great video to explain lora！ thanks

Is it okay to not scale the numerical data? Can we just proceed with the analysis as is?

can you please make a video on how to perform inference on VIT like googles open source vision transformer?

Great video! For me, the code makes it easier to understand the math than the actual formulas, so videos like these really help.

great video....

this is really amazing content but there is a problem on colab this code is not work anymore

great video , thanks for the work! here is a question from a complete beginner of mlflow and deployment: do I need 3 different machines to run the servers seperately ? Thanks!

Great talk. It’s very clearly explained and well presented.

good job!

For the line "from torch_geometric_temporal.dataset import METRLADatasetLoader" I am getting this error, "ModuleNotFoundError Traceback (most recent call last) <ipython-input-5-ab694df90048> in <cell line: 2>() 1 import numpy as np ----> 2 from torch_geometric_temporal.dataset import METRLADatasetLoader 3 from torch_geometric_temporal.signal import StaticGraphTemporalSignal 4 5 loader = METRLADatasetLoader() 3 frames /usr/local/lib/python3.10/dist-packages/torch_geometric_temporal/nn/attention/tsagcn.py in <module> 4 import torch.nn as nn 5 from torch.autograd import Variable ----> 6 from torch_geometric.utils.to_dense_adj import to_dense_adj 7 import torch.nn.functional as F 8 ModuleNotFoundError: No module named 'torch_geometric.utils.to_dense_adj'" Can you kindly guide that what could be the issue?

Excellent.

Explained quite well !

I've changed the output layer a bit... this: self.head_ln = nn.LayerNorm(emb_dim) self.head = nn.Sequential(nn.Linear(int((1 + self.height/self.patch_size * self.width/self.patch_size) * emb_dim), out_dim)) Then in forward: x = x.view(x.shape[0], int((1 + self.height/self.patch_size * self.width/self.patch_size) * x.shape[-1])) out = self.head(x) The downside is that you'll likely get a lot more overfitting, but without it the network was not really training at all.

BEST DIMENSIONAL REDUCTION VIDEO SERIES EVER! You are the 3blue1brown for data mining.

I think there is a confusion between cls token and positional embedding? At 6:09?

Finally a channel with good content!

hi there I have used the code for binary class classification, but encountering the problem on accuracy , showing 100% accuracy only on label 1 and some times on label 2. So it would be helpful for me if u provide me any solution

Very useful and informative video, especially PointNet and batch size parts. Special thanks for using point cloud domain!

Where to get slides? Used in video

how is Lora fine-tuning track changes from creating two decomposition matrix? How the ΔW is determined?

This channel is a gift

Ideot read paper. Lol

Your videos are great, super high quality and clear explanations. Thanks you so much!