Channel Avatar

DataMListic @UCRM1urw2ECVHH7ojJw8MXiQ@youtube.com

10K subscribers - no pronouns :c

Welcome to DataMListic (former WhyML)! On this channel I exp

Videos Posts Playlists
Recently Uploaded Popular Oldest
07:08
Multivariate Normal (Gaussian) Distribution Explained
04:29
Why Neural Networks Can Learn Any Function | The Universal Approximation Theorem
05:58
Mel Frequency Cepstral Coefficients (MFCC) Explained
14:44
Wav2vec2 A Framework for Self-Supervised Learning of Speech Representations - Paper Explained
03:55
Estimated Calibration Error (ECE) Explained (Model Calibration, Reliability Curve)
02:21
Why We Don't Accept The Null Hypothesis
08:04
P-Values Explained | P Value Hypothesis Testing
04:58
Why Residual Connections (ResNet) Work
05:40
Why Naive Bayes Is Naive
05:37
Why Neural Networks (NN) Are Deep | The Number of Linear Regions of Deep Neural Networks
09:04
ReLU Activation Function Variants Explained | LReLU | PReLU | GELU | SILU | ELU
07:55
Why Support Vector Machines (SVM) Are Large Margin Classifiers
09:01
Why ReLU Is Better Than Other Activation Functions | Tanh Saturating Gradients
08:59
Term Frequency Inverse Document Frequency (TF-IDF) Explained
09:29
Transformer Self-Attention Mechanism Explained | Attention Is All You Need
12:24
Why The Reset Gate is Necessary in GRUs
09:17
Gated Recurrent Unit (GRU) Equations Explained
11:05
Long Short-Term Memory (LSTM) Equations Explained
20:23
Connectionist Temporal Classification (CTC) Explained
03:44
Why Recurrent Neural Networks (RNN) Suffer from Vanishing Gradients - Part 2
12:58
Why Recurrent Neural Networks Suffer from Vanishing Gradients - Part 1
03:30
Why Weight Regularization Reduces Overfitting
04:02
Why Convolutional Neural Networks Are Not Permuation Invariant
02:42
Why We Need Activation Functions In Neural Networks
11:34
Why Minimizing the Negative Log Likelihood (NLL) Is Equivalent to Minimizing the KL-Divergence