Registration Form for cohort 1: https://forms.gle/gRqq7uCp9FVcqgej9
Notes about the course:
The course Text books:
- An Introduction to Statistical Learning: https://www.amazon.com/Introduction-Statistical-Learning-Applications-Statistics/dp/1461471370
- Machine Learning: A Probabilistic Perspective https://www.amazon.com/Machine-Learning-Probabilistic-Perspective-Computation/dp/0262018020
Instructor : Omid Safarzadeh:
LinkedIn: https://www.linkedin.com/in/omidsafarzadeh/
IG : @deepdatascientists
Supervised learning
Unsupervised learning
Semi-Supervised learning
Online Learning
Reinforcement Learning
Graph Representation Learning
Regression
The least squares approach
Multiple linear regression
Bias-variance tradeoff
Validation
Leave-one-out cross-validation
k-fold cross validation
logistic regression
MLE for simple logistic regression
Regularization
Ridge regression
Bias-variance tradeoff
Pros and cons of ridge regression
Likelihood and posterior distribution
Computing the posterior
Maximum likelihood estimation (MLE)
Maximum a posteriori (MAP) estimation
Posterior mean
MAP properties
Bayesian linear regression
Unsupervised learning
Principal component analysis (PCA)
Collaborative Filtering
Matrix Factorization
Funk SVD
Alternating Least Square
Expectation Maximization Algorithm
Clustering
K means
Gaussian Mixture Models
Activation Functions
Exponential Linear Unit (ELU)
Exponential activation function
Gaussian error linear unit (GELU)
Hard sigmoid
Rectified Linear Unit (ReLU)
Scaled Exponential Linear Unit (SELU)
Sigmoid
Softplus
Softsign
Swish
Hyperbolic Tangent
Loss Functions
Mean Absolute Error (MAE)
Mean Absolute Percentage Error (MAPE)
Mean Squared Error (MSE)
Mean Squared Error (MSE)
Indicator function
Gradient Decent
Back Propagation
CNN
RNN
LSTM
Sequence to sequence models
Attention Mechanism
Bottleneck Problem
Attention Layer
Categories of Attention Mechanism
Transformers
Self attention mechanism
Multi-Head attention mechanism
Encoder Architecture
Decoder Architecture
Full Architecture
Positional Encoding
BERT
Language Masked Learning
BERT Input
BERT Output
Motivation
Automatic FE with TensorFlow
Deep & Cross Network Structure
Pre Processing
Cross Network
Deep NN
Deep & Cross Network V1
Deep & Cross Network V2
Model construction
Model understanding for interpreting cross features
Model Performance