Deep Learning - Explicat in Limba Romana
Ghid interactiv pentru intelegerea conceptelor din cartea "Deep Learning" de Ian Goodfellow, Yoshua Bengio si Aaron Courville.
Click pe orice paragraf pentru a vedea simulari, referinte si animatii.
Felicitari!
Ai parcurs Capitolele 1-11 si 13 din "Deep Learning"!
Acum intelegi: istoria AI, algebra liniara (vectori, matrici, SVD, PCA), probabilitati (distributii, Bayes, expectatii), teoria informatiei (entropia, KL divergence, cross-entropy), calculul numeric (gradient descent, Hessian, optimizare constransa, KKT), machine learning basics (capacity, overfitting, regularization, MLE, SGD, manifold learning), retele feedforward (MLP, activari, backpropagation, grafuri computationale), regularizare pentru deep learning, optimizare (SGD, Momentum, Adam, Batch Normalization), retele convolutionale (CNN-uri, pooling, echivarianta, baza neurostiintifica), retele recurente (RNN, LSTM, GRU, attention, memory networks), metodologie practica (metrici, hyperparameter tuning, debugging) si linear factor models (PCA probabilistic, ICA, SFA, sparse coding)!
345 pagini explicate
850+ concepte cheie
345+ simulari interactive