Deep Learning with PyTorch

Deep Learning with PyTorch

• 1.
  Deep Learning without PhD,masters, graduation 
 Mayur Bhangale StoreKey
• 2.
  A Python basedscientific computing package targeted at two sets of audiences: • A replacement for numpy to use the power of GPUs • A deep learning research platform that provides maximum flexibility
 and speed
• 3.
  Basics
• 4.
  Variables, Tensors,
 Autograd
• 5.
  Predictive models Linear Regression •Fit a line to a data set of observations • Use this line to predict unobserved values
• 6.
  Predictive models Linear Regression Input x Output y mx+ c = y Linear Function 10 20 100 200 1.3 1.2 4.5 4.8
• 8.
  Predictive models Logistic Regression •Predicts the probability of occurrence of an event by fitting data to a logit function. • Used to predict a binary outcome (1 / 0, Yes / No, True / False) given a set of independent variables.
• 9.
  Predictive models Logistic Regression Input x Logits y mx+ c = y Linear Function 10 20 100 200 1.3 1.2 4.5 4.8 S = g(y) Softmax Function g(y) Softmax 0.1 0.1 0.4 0.4 D(S, L) Cross Entropy Function 0 0 1 1 L True Labels
• 10.
  Predictive models Input x Logits y Linear Function Softmax Function g(y) Softmax D(S, L) Cross Entropy Function Labels L TrueLabels Readout LayerInput Layer Output Layer Logistic Regression
• 11.
  Predictive models Input x Logits y Linear Function Softmax Function g(y) Softmax Cross Entropy Function Labels L True Labels ReadoutLayerInput Layer Output Layer Example Size: 784 Size: 10
• 13.
  Convolutional Neural Network
• 14.
  Thank you Mayur Bhangale [email protected] mayurbhangalemayurcbmayurbhangale