Qixin Wang 2016-01-25

Work done in this week

word vector size:200

hidden size:500

mlp hidden size:400

maxout size:300

adadelta 0.3

---

fast mode, added cut, no global, no pz

zgt:song, si, giga, update: (grid-9, grid-9, grid-17, grid-17)

psm:song, si, giga, update: (grid-15, grid-15, grid-13, grid-11)

---

with dropout & without maxout:

batch_all(zgt): grid-12

batch_all_go(zgt): grid-11

---

batch training code:

doing debug

---

int32 * float32 -> float64

float32 * float32 -> float32

---

fix n*bugs

added maxout

added update vectors

added dropout

deleted some long 224 iambic (length > 120)

---

for 2.1

mini_batch data parallel training

400k sentences per day (Iambic are longer than QA questions), up to 50X times faster! (now as faster as Bengio's code)

but still fast enough for the 15k song iambics......