Mac Eclipse Debugging So Slow! Life saver tip!

If debugging in eclipse in mac has been so slow for you here is the solution: close the Variables window and what ever you wanna see hover over its variabel or add it to the watch list

Source: http://stackoverflow.com/questions/6893553/why-is-debugging-in-eclipse-pydev-so-slow-for-my-python-program

How to Receive Files in your Google Drive from Anyone

A school teacher wants to have a public drop box (not Dropbox) where students can upload homework assignments. A recruiter wants to have an online form where job applicants can upload their resumes. A designer may need a public drop box where clients can upload photographs easily.

Import iPhone Images to MAc without iPicture

Step 1Connect your iPhone to your Mac with its USB cord. Wait a moment for your Mac to recognize that it has been connected.

Step 2Click the "Finder" button in the Dock and click the "Applications" folder in the left pane. Scroll through the list of applications to "Image Capture" and double-click it to open it.

Step 3Select a location on your Mac for the Image Capture application to save your iPhone pictures. To delete the pictures from your iPhone upon completion, click "Options," open the "Options" tab and select "Delete Items from Camera after Downloading."

Step 4Click the "OK" button and then click the "Download All" button to transfer the photos. Once complete, you can disconnect your iPhone from your computer.
 

 

Source: http://everydaylife.globalpost.com/transfer-photos-iphone-mac-iphoto-29666.html

Scaling up Deep Learning Using a GPU Cluster

If you may know Andre Ng made a big noise by using deep learning for a cat detecting tool that cost about $1M. In this ICML paper, he describes how you can build pretty much the same thing for jsut about $20,000. Worth a read: Deep learning with COTS HPC systems

On Deciding between MongoDB vs MySQL

MongoDB offers sharding by key for horizontal scaling when doing fanout wirte or read depending on application: link

On the other hand

Deep Learning Plays Attari

Deep Mind, a subsidary of Google published an extended version of their 2013 paper in Nature along with source codes. Nature Paper. Code. The big picture: a deep network that has loss function as a function that maximizes its score. The input is the pixels of the screen (state) and output is action+score

Building a PC Tower for Deep Learning

It's been a while that I have not looked into building a PC piece by piece and I had to refresh my rusty knowledge. First you'd want to take a look at these: Which GPU(s) to Get for Deep Learning, which suggests for GTX 980 and GTX Titan and Which GPU to use for deep learning? that sugegsts GTX 780TI as a top mid-range. There is also this, which is a good quick guide on building a PC. So, here it boils down to two main goals: take the biggest memory on a cuda-enabled GPU which means NVIDIA. AMD on the other hand offers OpenCL library but I would say you won't find any deep learning library using OpenCL. So stick to NVIDIA, and any recent NVIDIA will do.

Such a system will be single threaded deep learning algorithm, so CPU does not play any roles here. The faster matrix computations the farther you'll get.

NVIDIA offers several categories of GPUs (Geforce, Tesla, Quadro).

Getting the Power of GPU for Deep Learning

install EPD
install bleeding edge theano

On my macbook pro it says my graphics card is Intel HD Graphics 4000 1024 MB. I was very disappointed that Apple just left an intel graphics card on a $2000 laptop. They could definitely do better. So I gave up on CUDA. Recently I found that two graphics cards on board!

Visualizing Optimization Algorithms

Here we look at a visualization of optimization algorithms:
- SGD (Stochastic Gradient Descent)
- Momentum
- NAG  (Numerical Algorithms Group)
- Adagrad (Adaptive Gradient Algorithm)
- Adadelta
- RMSProp (Divide the gradient by a running average of its recent magnitude)

What we are missing is the L-BFGS (Limited-memory BFGS)...

Deep Learning: Theano vs Torch vs Caffe vs deeplearning4j?

I am using deeplearning for hyperspectral data and I had to decide between available frameworks.

  Theano vs Torch vs Caffe vs deeplearning4j