Viewing profile — rudyl313

One thing to keep in mind is that predicting a downturn in the short-term is different than predicting long-run performance over 10, 20 or 30 years. I think the website is trying t…

"If you really want to own a stock that gives you no profits, no income from dividends, no voice in how its run, and actually no value what so ever other than the greater fool theo…

I've written up my philosophy on beating the market, which is a little less conservative with respect to believing that markets are efficient and investing in the indices is the on…

Using ReLU units is a newer advancement and I agree that changing the activation function does change the cost function. However, before Hinton got all excited about ReLU units, he…

But the tricks/advancements I mentioned are not changing the function. They changed the initial weights and how the cost function was explored.

If these claims are true (specifically, that every local minimum is a global minimum), then why did the earlier neural networks have poor performance? Why did we need advancements …

The market movement can be explained somewhat by the fed's rate hike expectations changing (worsening economic conditions means that the fed is more cautious about raising rates, s…

Unfortunately this talk is kind of dated already. Most people don't stack RBMs or autoencoders to pretrain the weights anymore. If you use dropout with rectified linear units, you …

A placebo won't work if you know it's a placebo.

Very cool! Thanks for sharing that

I love to watch tech talks over dinner every evening, but I'm starting to run out. What are some of the best sources for tech talks?