Thanks for making this book available.
In the toy example 8.1.2, when creating the dataset, I was wondering if it was normal for both the train set and the test set to be the same. Namely:
train_iter = d2l.load_array((features[:n_train], labels[:n_train]), batch_size, is_train=True) test_iter = d2l.load_array((features[:n_train], labels[:n_train]), batch_size, is_train=False)
For test_iter, I would have expected something like:
test_iter = d2l.load_array((features[n_train:], labels[n_train:]), batch_size, is_train=False)
Thanks for your time.
Great catch @dosssman! I believe we don’t need
test_iter, as it is never used after being defined.
I see. I did not get that far down yet haha.
8.1.2. A Toy Example
features = d2l.zeros((T-tau, tau))
AttributeError : module ‘d2l.torch’ has no attribute ‘zeros’
Then I search http://preview.d2l.ai/d2l-en/PR-1077/search.html?q=d2l.zeros&check_keywords=yes&area=default
No source code:
I can use ``features = d2l.torch.zeros((T-tau, tau))` to replace now, and try to code next time!
An hour to debug!
Hi @StevenJokes, great try! Your effort will ultimately gain some tractions!
for i in range(tau): features[:, i] = x[i: i + T - tau - max_steps + 1].T
What’s the purpose of
.T at the end of the line above? It seems making no difference
I can’t agree more. Transposing a 1-rank tensor returns exactly itself.
Also this code
for i in range(n_train + tau, T): multistep_preds[i] = d2l.reshape(net( multistep_preds[i - tau: i].reshape(1, -1)), 1)
can be simply written as
for i in range(n_train + tau, T): multistep_preds[i] = net(multistep_preds[i - tau: i])
I agree. Fixing: https://github.com/d2l-ai/d2l-en/pull/1542
Next time you can PR first: http://preview.d2l.ai/d2l-en/master/chapter_appendix-tools-for-deep-learning/contributing.html
I couldn’t help but notice the similarities between the latent autoregressive model and hidden Markov models. The difference being that in the case of latent autoregressive model the hidden sequence h_t might change over time t and in the case of Hidden markov models the hidden sequence h_t remains the same for all t. Am I correct in assuming this?
I have a question about math. In particular what does the sum on x_t in eqution 8.1.4 mean?
Is that the sum over all the possible state x_t? But that does not make a lot of sense to me, because if I have observed x_(t+1) there is just one possible x_t.
Could someone help me in understanding that?
Thanks a lot!