Deep Learning and Natural Language Processing

Hands-on: Logistic regression.py

torch.manual_seed(123)

# TODO: Generate 2 clusters of 100 2d vectors, each one distributed normally, using
# only two calls of randn()
classApoints =
classBpoints =

# TODO: Add the vector [1.0,3.0] to the first cluster and [3.0,1.0] to the second.
classApoints += 
classBpoints +=

# TODO: Concatenate these two clusters along dimension 0 so that the points
# distributed around [1.0, 3.0] all come first
inputs =

# TODO: Create a tensor of target values, 0 for points for the first cluster and
# 1 for the points in the second cluster. Make sure that these are LongTensors.
classA = 
classB = 
targets = torch.cat([classA, classB])

# TODO: Set the random seed to 123 using manual_seed


# TODO: Initialize a Linear layer to output scores 
# for each class given the 2d examples
model =

# TODO: Define your loss function
loss_fn = 

# TODO: Initialize an SGD optimizer with learning rate 0.1
optimizer = 

# Train the model for 100 epochs 
n_epochs = 100
losses = []
for _ in range(n_epochs):
  optimizer.zero_grad() 
  preds = model(inputs)
  loss = TODO
  losses.append(loss)
  loss.backward()
  optimizer.step()
print(f'Anwswer to Exercise 6: Loss after {n_epochs} epochs: {losses[-1]}')
      
iterations = np.arange(len(losses))
_ = plt.plot(iterations, losses, '', iterations, losses, '-')